© 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. 87082
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Abort
    -0.26
     lingu
    -0.26
     occas
    -0.26
    imate
    -0.25
    ENTS
    -0.25
    dj
    -0.25
    ὶ
    -0.24
    ç«ĭæĸ¹
    -0.24
    miss
    -0.24
    isson
    -0.24
    POSITIVE LOGITS
    orn
    0.28
    åĽŀ头çľĭ
    0.28
    Âł
    0.27
    ãģ¯ãģĺãĤģ
    0.26
    aday
    0.26
     https
    0.26
    ouser
    0.25
     ÑģпÑĢав
    0.25
    inea
    0.24
     ahead
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.