© 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. 86642
    Prev
    Next
    INDEX
    Explanations

    Game code

    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
     thư
    -0.08
    桨
    -0.06
    (parcel
    -0.06
    _CANCEL
    -0.06
     nause
    -0.06
    __(*
    -0.06
    忤
    -0.06
    瑢
    -0.06
    (do
    -0.06
     savory
    -0.06
    POSITIVE LOGITS
    rows
    0.07
    sets
    0.07
     Rogers
    0.07
    _padding
    0.07
    щение
    0.07
    legen
    0.07
    されていた
    0.06
    していた
    0.06
    ⼊
    0.06
    わかって
    0.06
    Activations Density 0.011%

    No Known Activations