© 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. 19-RESID-POST-AA
    11. 75599
    Prev
    Next
    INDEX
    Explanations

    answering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Favorite
    -0.08
    _fs
    -0.07
    -default
    -0.07
    础
    -0.07
    =back
    -0.07
     VW
    -0.07
    构建
    -0.06
    布置
    -0.06
    Wifi
    -0.06
    рен
    -0.06
    POSITIVE LOGITS
    สยาม
    0.07
    おかげ
    0.07
    皦
    0.07
     attackers
    0.07
     act
    0.06
    Schedule
    0.06
    /he
    0.06
    ימים
    0.06
     patriot
    0.06
    .runtime
    0.06
    Activations Density 0.020%

    No Known Activations