© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40062
    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
    Not in Any Lists

    No Comments

    Negative Logits
    emon
    -0.29
    sessions
    -0.27
    chk
    -0.27
     Abdel
    -0.26
    #
    -0.26
    suite
    -0.25
     Pub
    -0.24
     chk
    -0.24
     æŁ¥
    -0.24
    NR
    -0.24
    POSITIVE LOGITS
     shaped
    0.30
     ideal
    0.30
     mesh
    0.28
     mund
    0.28
    <quote
    0.28
     scene
    0.27
     wave
    0.27
     clim
    0.27
     poles
    0.27
     flown
    0.26
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.