© 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. 30-TRANSCODER-HP
    7. 96699
    Prev
    Next
    INDEX
    Explanations

    Sugar related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntag
    -0.32
     tag
    -0.27
    _marker
    -0.26
     Riders
    -0.26
    -bars
    -0.25
     insiders
    -0.25
     pinned
    -0.25
    vak
    -0.25
     challeng
    -0.25
     Reco
    -0.24
    POSITIVE LOGITS
    agal
    0.39
    ç³ĸ
    0.37
     gly
    0.36
     sugar
    0.36
    gly
    0.34
     gal
    0.33
     sugars
    0.31
    mann
    0.30
     glucose
    0.30
     xy
    0.29
    Activations Density 1.419%

    No Known Activations