© 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. 63492
    Prev
    Next
    INDEX
    Explanations

    technology and research

    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
    serter
    -0.30
    è¦ģçŁ¥éģĵ
    -0.29
    æī¾ä¸ª
    -0.28
    .herokuapp
    -0.28
    åħ¥å¸Ĥ
    -0.27
    _renderer
    -0.26
    onium
    -0.26
    icum
    -0.26
    -ground
    -0.26
    theid
    -0.25
    POSITIVE LOGITS
    æīģ
    0.28
     marsh
    0.27
    ow
    0.26
    èµĵ
    0.26
    ree
    0.26
    /
    0.26
    æļĸ
    0.26
    åı¥
    0.26
    ç§į
    0.25
    -
    0.25
    Activations Density 42.194%

    No Known Activations