© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111151
    Prev
    Next
    INDEX
    Explanations

    transparency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ì°¨
    -0.30
    æł¸å¿ĥæĬĢæľ¯
    -0.26
     Nearby
    -0.25
     exile
    -0.25
    å·²ä¹ħ
    -0.25
    ãĥ¥ãĥ¼
    -0.23
     Vintage
    -0.23
    DN
    -0.23
    IgnoreCase
    -0.23
    天é¹ħ
    -0.23
    POSITIVE LOGITS
    ly
    0.33
    èµ·
    0.30
    fulness
    0.28
     dec
    0.26
    ament
    0.25
    بة
    0.25
    åĢĴåľ¨
    0.24
    ilo
    0.24
     order
    0.24
    å½»
    0.24
    Activations Density 0.031%

    No Known Activations