© 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. 35-TRANSCODER-HP
    7. 38758
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     bureaucr
    -0.27
     enr
    -0.27
    BBBB
    -0.26
    poi
    -0.26
    Enterprise
    -0.26
    èĻ»
    -0.25
    _bp
    -0.25
    åħħ满äºĨ
    -0.24
    罩
    -0.24
     createState
    -0.24
    POSITIVE LOGITS
     individual
    0.34
     dual
    0.30
     minor
    0.29
     future
    0.28
     far
    0.28
     typical
    0.28
     slight
    0.25
    ä¸ĭ车
    0.25
     visibility
    0.25
    vis
    0.25
    Activations Density 3.917%

    No Known Activations

    This feature has no known activations.