Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 27302
    Prev
    Next
    INDEX
    Explanations

    the

    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
     tasting
    -0.07
     Scalia
    -0.07
    飛び
    -0.06
    怎么
    -0.06
    .Dispatcher
    -0.06
    spawn
    -0.06
    抽烟
    -0.06
    IFDEF
    -0.06
     afraid
    -0.06
     Phen
    -0.06
    POSITIVE LOGITS
    ,$
    0.08
    ]=$
    0.08
    �
    0.07
    .MessageBox
    0.07
    钤
    0.07
    梓
    0.07
    onitor
    0.07
    켰
    0.07
    mw
    0.07
    했습니다
    0.07
    Activations Density 0.055%

    No Known Activations