© 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. 19-RESID-POST-AA
    11. 90028
    Prev
    Next
    INDEX
    Explanations

    radial

    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
    请求
    -0.07
    ús
    -0.07
    סול
    -0.07
    His
    -0.07
    	host
    -0.07
     kissing
    -0.06
    rolled
    -0.06
     Tom
    -0.06
    culus
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    Abort
    0.07
     Emin
    0.07
    建造
    0.07
     Formatter
    0.07
     +-
    0.06
     ageing
    0.06
    למיד
    0.06
     أو
    0.06
     retention
    0.06
    结论
    0.06
    Activations Density 0.002%

    No Known Activations