© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 2055
    Prev
    Next
    INDEX
    Explanations

    legal, technical documents/discussions

    np_max-act · gemini-2.0-flash

    language about evaluating or structuring content—such as giving ratings, scores, feedback, or instructions related to questions, answers, and document format.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /head
    -0.07
     }
    ↵
    ↵
    ↵
    ↵
    -0.07
    "$
    -0.07
    ):
    ↵
    -0.07
     הק
    -0.07
    .".
    -0.07
    _force
    -0.07
    _viewer
    -0.07
    }↵↵↵↵↵↵
    -0.06
    '></
    -0.06
    POSITIVE LOGITS
     PLAY
    0.09
    韫
    0.07
    יפים
    0.07
     clearColor
    0.07
    掂
    0.07
     XCTest
    0.06
    🟢
    0.06
    ˥
    0.06
     Hãy
    0.06
    醛
    0.06
    Activations Density 1.436%

    No Known Activations