© 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. 20-TRANSCODER-HP
    7. 106937
    Prev
    Next
    INDEX
    Explanations

    English language text

    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
     puss
    -0.28
     kull
    -0.26
    äºĮ线
    -0.26
    åħ³èģĶ
    -0.26
    çĶŁäº§æĢ»åĢ¼
    -0.26
    гаÑĢ
    -0.26
     combo
    -0.25
    äº
    -0.25
     contender
    -0.24
     LIN
    -0.24
    POSITIVE LOGITS
    ä¸ľè¥¿
    0.30
    ...
    0.28
    ĥģ
    0.25
    åŁ¹åħ»
    0.25
     Rat
    0.25
    AtPath
    0.25
    .gradle
    0.24
     Hath
    0.24
     Tight
    0.24
    âĢ¦
    0.24
    Activations Density 6.230%

    No Known Activations