© 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. 68981
    Prev
    Next
    INDEX
    Explanations

    makeup

    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
    odies
    -0.07
     objs
    -0.07
     Между
    -0.07
     nuestras
    -0.07
    Ghost
    -0.07
     candies
    -0.07
    _left
    -0.07
    欢乐
    -0.07
    ตำบ
    -0.07
    minecraft
    -0.07
    POSITIVE LOGITS
    还
    0.07
    报道
    0.07
     Basketball
    0.07
    膦
    0.06
    Թ
    0.06
    -Jun
    0.06
    먼
    0.06
    發表
    0.06
    stituição
    0.06
    ramework
    0.06
    Activations Density 0.000%

    No Known Activations