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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129938
    Prev
    Next
    INDEX
    Explanations

    programming/research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apolis
    -0.28
     MySql
    -0.27
    enberg
    -0.25
    伶
    -0.23
    ktop
    -0.23
     seas
    -0.23
    ä¸įä¹ı
    -0.23
    cision
    -0.23
    apest
    -0.23
    ä¸ĢéĿ¢
    -0.23
    POSITIVE LOGITS
    rams
    0.26
    èį»
    0.25
    ovan
    0.25
    remen
    0.25
    æīĢåľ¨åľ°
    0.24
    -pos
    0.24
    asic
    0.24
    å¼
    0.24
    iscal
    0.23
    fan
    0.23
    Activations Density 0.012%

    No Known Activations