© 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. 142091
    Prev
    Next
    INDEX
    Explanations

    analyzing data

    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
     ÅŁek
    -0.28
    arily
    -0.27
    culos
    -0.26
     vez
    -0.25
    emet
    -0.25
    utex
    -0.24
    orarily
    -0.24
     resume
    -0.24
    èĩªå¦Ĥ
    -0.24
    éĦĹ
    -0.24
    POSITIVE LOGITS
    åIJĮæĥħ
    0.28
    第äºĮç§į
    0.27
    Matchers
    0.25
    æĸ°åŀĭ
    0.25
     particularly
    0.25
    Anth
    0.24
    认è¯Ĩ
    0.24
    inous
    0.24
    Later
    0.24
    particularly
    0.23
    Activations Density 2.199%

    No Known Activations