© 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. 11-RESID-POST-AA
    11. 25542
    Prev
    Next
    INDEX
    Explanations

    Expressing enjoyment of food

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    合计
    -0.07
     claro
    -0.07
     perí
    -0.07
    ({_
    -0.07
    戋
    -0.07
    点赞
    -0.07
    reve
    -0.07
    无疑
    -0.07
    ическ
    -0.07
    .Day
    -0.07
    POSITIVE LOGITS
     father
    0.08
    粱
    0.07
     priorit
    0.07
     Restoration
    0.07
     дети
    0.07
    屠杀
    0.07
     restoration
    0.07
    (ret
    0.07
    שילוב
    0.07
     Writing
    0.07
    Activations Density 0.035%

    No Known Activations