© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19939
    Prev
    Next
    INDEX
    Explanations

    Crossed arms or legs

    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
    瞻
    -0.07
     depart
    -0.07
    ));
↵
↵
    -0.07
     &&
↵
    -0.07
    "))
↵
    -0.07
    CES
    -0.07
     lunch
    -0.06
     tant
    -0.06
    沦为
    -0.06
    顶
    -0.06
    POSITIVE LOGITS
    ,G
    0.07
     pakistan
    0.07
    gies
    0.07
     gene
    0.07
    callable
    0.07
    _rot
    0.07
    隐身
    0.07
    (g
    0.07
    -users
    0.07
     proj
    0.07
    Activations Density 0.003%

    No Known Activations