© 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. 53913
    Prev
    Next
    INDEX
    Explanations

    Code or markup language

    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
     lo
    -0.30
     o
    -0.30
    èµĪ
    -0.28
    å¼Ĥ
    -0.27
    Sub
    -0.27
     dimensions
    -0.25
    _o
    -0.25
     op
    -0.25
     RX
    -0.25
    opl
    -0.25
    POSITIVE LOGITS
    UCE
    0.27
    æģ¯
    0.26
    /inet
    0.25
    bole
    0.25
    ï½ĸ
    0.25
    游æĪıä¸Ń
    0.24
    tÃŃ
    0.24
    åIJĪæł¼
    0.24
    uran
    0.23
    vider
    0.23
    Activations Density 0.006%

    No Known Activations