© 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. 40195
    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
     pylab
    -0.28
     Assumes
    -0.27
     anmeld
    -0.25
    以æѤ
    -0.24
    -LAST
    -0.24
    째
    -0.24
    idot
    -0.23
     endforeach
    -0.23
     Anch
    -0.23
    涣
    -0.23
    POSITIVE LOGITS
     experienced
    0.30
     key
    0.29
    éĻ
    0.25
     relief
    0.25
     pack
    0.24
    king
    0.24
     view
    0.24
     puzzle
    0.23
     mini
    0.23
     pay
    0.23
    Activations Density 0.359%

    No Known Activations

    This feature has no known activations.