© 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. 11313
    Prev
    Next
    INDEX
    Explanations

    disclaims

    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
    每一天
    -0.08
    仅供
    -0.07
    ѫ
    -0.07
     consts
    -0.07
     Likely
    -0.07
    不然
    -0.07
    gmt
    -0.07
    /application
    -0.07
    搡
    -0.07
    ghi
    -0.07
    POSITIVE LOGITS
     violate
    0.08
    [element
    0.08
    運用
    0.07
    unas
    0.07
     usernames
    0.07
    펠
    0.07
     automát
    0.07
    ACHED
    0.07
     reserva
    0.06
    reb
    0.06
    Activations Density 0.001%

    No Known Activations