© 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. 41965
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ebb
    -0.28
    oppable
    -0.28
    latent
    -0.27
    ONA
    -0.26
     talent
    -0.26
     talents
    -0.26
    fab
    -0.26
    座
    -0.24
     squeezed
    -0.24
     urgent
    -0.23
    POSITIVE LOGITS
     history
    0.75
     History
    0.66
    åİĨåı²
    0.64
    history
    0.63
    History
    0.62
    -history
    0.60
     histories
    0.60
    _history
    0.58
    .history
    0.52
     activity
    0.50
    Activations Density 0.003%

    No Known Activations