© 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. 53674
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific texts

    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
    (arc
    -0.64
     arc
    -0.61
    arc
    -0.60
    Arc
    -0.57
     arch
    -0.56
    弧
    -0.55
     arcs
    -0.54
     Arc
    -0.54
    _arc
    -0.52
    æĭ±
    -0.52
    POSITIVE LOGITS
     Cros
    0.29
     brink
    0.26
    讼
    0.25
    fäh
    0.25
    reate
    0.25
    DbType
    0.25
     fines
    0.25
     brightest
    0.24
     ground
    0.24
    pletely
    0.23
    Activations Density 0.009%

    No Known Activations