© 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. 63861
    Prev
    Next
    INDEX
    Explanations

    Explanations of reasons or goals

    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
    aco
    -0.27
    OSE
    -0.25
    ç»ĵ
    -0.25
    .nodeName
    -0.25
    åı¯èĥ½åıijçĶŁ
    -0.24
    å´ĩæĭľ
    -0.24
     OSD
    -0.24
    ellt
    -0.23
    eya
    -0.23
    İ·
    -0.23
    POSITIVE LOGITS
     nevertheless
    0.26
    å§Ķ
    0.26
    iped
    0.26
    -<?
    0.25
     bytearray
    0.25
     CAST
    0.24
     lash
    0.24
    å¨ĺ家
    0.24
     Emanuel
    0.24
    лаÑģ
    0.24
    Activations Density 0.211%

    No Known Activations