© 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. 39937
    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
     Cells
    -0.29
     cells
    -0.29
    (location
    -0.28
     Sug
    -0.28
    cells
    -0.28
     located
    -0.28
    ä½įç½®
    -0.27
    èĥŀ
    -0.26
     location
    -0.26
     Cell
    -0.26
    POSITIVE LOGITS
     voyeur
    0.27
     recorder
    0.27
     encoder
    0.26
     gesture
    0.25
     remot
    0.25
     sniff
    0.25
     bundle
    0.25
     viper
    0.25
     bund
    0.24
     motors
    0.24
    Activations Density 5.336%

    No Known Activations

    This feature has no known activations.