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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12433
    Prev
    Next
    INDEX
    Explanations

    says

    np_max-act · gemini-2.0-flash

    journalistic attribution phrases indicating that a named person is speaking or being quoted.

    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
     Surface
    -0.07
    urd
    -0.07
     Tư
    -0.07
    unks
    -0.06
    建设用地
    -0.06
    赌博
    -0.06
     NPCs
    -0.06
     YOU
    -0.06
    一间
    -0.06
    (Board
    -0.06
    POSITIVE LOGITS
     ","↵
    0.07
    行星
    0.07
     ingest
    0.07
    קבוצות
    0.07
    熊猫
    0.07
    冤
    0.07
    齊
    0.06
    designation
    0.06
     Elis
    0.06
    אוניברס
    0.06
    Activations Density 0.027%

    No Known Activations