© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 39612
    Prev
    Next
    INDEX
    Explanations

    URLs/Documentation

    np_max-act · gemini-2.0-flash
    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
     taking
    -0.07
    民主党
    -0.07
    _Send
    -0.07
    他是
    -0.07
    征求意见
    -0.07
     millones
    -0.07
     Dean
    -0.07
     abuse
    -0.07
    巽
    -0.07
     congregation
    -0.07
    POSITIVE LOGITS
     retard
    0.07
    vard
    0.07
     ogs
    0.07
    parallel
    0.06
     Incre
    0.06
    (`<
    0.06
    vc
    0.06
    钣
    0.06
    rawer
    0.06
    蟆
    0.06
    Activations Density 0.026%

    No Known Activations