© 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. 111144
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     cunt
    -0.27
    å¿ĺ
    -0.26
    æĽ¿
    -0.25
     Kens
    -0.25
    -reaching
    -0.24
     XR
    -0.24
    CTION
    -0.24
    ronic
    -0.24
     hei
    -0.24
    viron
    -0.24
    POSITIVE LOGITS
    @Module
    0.27
    ograd
    0.26
    edImage
    0.26
    .modules
    0.26
    WithType
    0.25
    .Modules
    0.25
     //~
    0.24
    ocache
    0.24
    棱
    0.24
    è¡Į车
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.