© 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. 63500
    Prev
    Next
    INDEX
    Explanations

    dollars

    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
    çĶĺ
    -0.27
    nad
    -0.25
    Ack
    -0.25
     Farrell
    -0.25
    tip
    -0.25
    ommen
    -0.25
    facet
    -0.25
    çŃĨ
    -0.25
    ictured
    -0.25
     Ack
    -0.24
    POSITIVE LOGITS
    èĤī
    0.30
    åĬŀ
    0.28
    æĶ¶åĽŀ
    0.25
    åĩºå¢ĥ
    0.24
    ç§ijæĬĢèĤ¡ä»½
    0.24
     owned
    0.24
    绣ä¸Ģ
    0.23
    /year
    0.23
     valuation
    0.23
    atto
    0.23
    Activations Density 5.474%

    No Known Activations