© 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. 130295
    Prev
    Next
    INDEX
    Explanations

    documentation

    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
    º«
    -0.27
    å¸ĪåĤħ
    -0.26
    opp
    -0.25
    ä¸ĩ人
    -0.25
    åįĥä¸ĩ
    -0.25
    å®ļå¾ĭ
    -0.25
    å¨ģ
    -0.25
    amples
    -0.24
    {o
    -0.24
    å°ij
    -0.24
    POSITIVE LOGITS
    UnityEngine
    0.28
    ç»ıèIJ¥æ´»åĬ¨
    0.25
    åŁºç¡Ģ
    0.25
    åľ°æĸ¹æĶ¿åºľ
    0.25
    ysz
    0.24
    ä¸IJ
    0.24
    eses
    0.24
    èĬ¥
    0.24
    ibling
    0.24
    解åĨ³éĹ®é¢ĺ
    0.24
    Activations Density 75.685%

    No Known Activations