© 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. 31-TRANSCODER-HP
    7. 18583
    Prev
    Next
    INDEX
    Explanations

    result

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VB
    -0.29
    omers
    -0.26
    arp
    -0.26
    witter
    -0.26
    asthan
    -0.25
    VA
    -0.25
    vb
    -0.25
    fal
    -0.25
    Ñģад
    -0.23
    stem
    -0.23
    POSITIVE LOGITS
    èĩ´
    0.85
     èĩ
    0.62
    èĩ³
    0.54
    ç
    0.48
    æĪIJ
    0.39
    èĩ³äºİ
    0.39
    èĩ³æĸ¼
    0.35
     dazu
    0.31
    èĩ´è¾ŀ
    0.29
    _into
    0.28
    Activations Density 15.107%

    No Known Activations