© 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. 33-TRANSCODER-HP
    7. 54047
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trim
    -0.26
     bridge
    -0.24
    åIJ¸å¼ķæĽ´å¤ļ
    -0.24
    Raised
    -0.24
     trim
    -0.24
     wei
    -0.24
    [$_
    -0.24
     brid
    -0.24
     enemies
    -0.23
     ``
    -0.23
    POSITIVE LOGITS
    orz
    0.28
    ippo
    0.27
     гаÑĢ
    0.25
    OR
    0.24
    á»ĩt
    0.24
    è·ĭ
    0.23
    kek
    0.23
     stemmed
    0.23
    TECTED
    0.23
     (£
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.