© 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. 129075
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Negative Logits
    å²Ľå±¿
    -0.27
    PropertyValue
    -0.27
     projected
    -0.25
     occupation
    -0.25
    åĽ½åº¦
    -0.24
    лиÑģÑĤ
    -0.24
     Fuck
    -0.24
    对åºĶ
    -0.24
    áng
    -0.24
    _DIRECTION
    -0.24
    POSITIVE LOGITS
    ="--
    0.28
    beat
    0.26
    åİŁæľīçļĦ
    0.26
     beats
    0.25
    åİŁæľī
    0.25
    erge
    0.25
     univers
    0.25
    åİĨæĿ¥
    0.24
     Beg
    0.24
    CHK
    0.24
    Activations Density 35.093%

    No Known Activations

    This feature has no known activations.