© 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. 63957
    Prev
    Next
    INDEX
    Explanations

    Biology and computing

    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
    èĨº
    -0.30
    å±¥èģĮ
    -0.27
     eer
    -0.27
     previously
    -0.27
     Previously
    -0.27
    ToObject
    -0.26
    å¾Īæĺİæĺ¾
    -0.25
    æ¦Ĥ
    -0.25
    大æ¦Ĥ
    -0.25
    ä¹ĭåīį
    -0.25
    POSITIVE LOGITS
    è¯įæĿ¡
    0.27
     Ñģл
    0.26
    Advertisements
    0.26
     WARRANTIES
    0.25
    ä¸ĢéĶ®
    0.25
    Ñģкие
    0.25
    achs
    0.24
    Exactly
    0.24
    ä¸ĸçķĮ第ä¸Ģ
    0.24
    uario
    0.24
    Activations Density 15.249%

    No Known Activations