© 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. 32-TRANSCODER-HP
    7. 42450
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¥Ī
    -0.28
    warf
    -0.26
    scient
    -0.26
    Pred
    -0.26
     Met
    -0.26
    .Offset
    -0.25
     Pred
    -0.25
     space
    -0.25
     spy
    -0.24
    空éĹ´
    -0.24
    POSITIVE LOGITS
    ters
    0.30
    æĭī
    0.27
    Flip
    0.27
    ç¿»
    0.26
     flip
    0.26
    hä
    0.26
    rios
    0.25
    otal
    0.25
    omba
    0.25
    -sizing
    0.25
    Activations Density 0.000%

    No Known Activations