© 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. 53417
    Prev
    Next
    INDEX
    Explanations

    people expressing opinions

    np_max-act-logits · gemini-2.0-flash
    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
     Updates
    -0.29
     Builds
    -0.26
    Updates
    -0.25
    _EOL
    -0.25
    æ´»
    -0.24
    thed
    -0.24
     resets
    -0.24
    ittest
    -0.24
     Changes
    -0.24
    GLE
    -0.23
    POSITIVE LOGITS
     left
    0.42
    _left
    0.31
     Left
    0.30
     heads
    0.30
    纳æĸ¯
    0.30
     provided
    0.29
     called
    0.29
     happens
    0.29
     happen
    0.29
     extended
    0.28
    Activations Density 0.119%

    No Known Activations