© 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. 88765
    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
     testData
    -0.27
    çIJĨ
    -0.26
    linger
    -0.26
     */)
    -0.25
    aData
    -0.24
     OSD
    -0.24
     OPS
    -0.23
    ç§¦åĽ½
    -0.23
    çļĭ
    -0.23
    apol
    -0.23
    POSITIVE LOGITS
    æīĵåħ¥
    0.27
     bur
    0.25
    éªĸ
    0.25
    åĶ³
    0.25
    boxed
    0.25
    èı©æıIJ
    0.24
    _trait
    0.24
     nor
    0.24
     allowable
    0.23
    ables
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.