© 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. 20-TRANSCODER-HP
    7. 107611
    Prev
    Next
    INDEX
    Explanations

    Measurements and quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    axy
    -0.28
     -------------------------------------------------------------------------↵
    -0.27
    rost
    -0.25
    pai
    -0.25
    ertia
    -0.25
    循çݯç»ıæµİ
    -0.24
     skype
    -0.24
    зон
    -0.24
    gment
    -0.23
    iona
    -0.23
    POSITIVE LOGITS
    çģ¿çĥĤ
    0.28
    让å®ĥ
    0.28
    åİŁæĿ¥æĺ¯
    0.28
    使åħ¶
    0.27
    为äºĨ让
    0.26
    èĤ¯å®ļæĺ¯
    0.26
    åıĺéĿ©
    0.25
    çĽ¼
    0.25
    æĬĬå®ĥ
    0.25
    coder
    0.24
    Activations Density 17.590%

    No Known Activations