© 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. 42114
    Prev
    Next
    INDEX
    Explanations

    pin

    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
    adan
    -0.28
    bab
    -0.28
     bic
    -0.26
    alis
    -0.26
    TED
    -0.26
    ISIS
    -0.25
    iman
    -0.25
    ovenant
    -0.24
    dex
    -0.24
    xbb
    -0.24
    POSITIVE LOGITS
     pin
    1.03
    pin
    0.97
    Pin
    0.95
     Pin
    0.95
    -pin
    0.86
     pins
    0.86
    _pin
    0.82
    (pin
    0.81
     PIN
    0.74
    PIN
    0.74
    Activations Density 0.002%

    No Known Activations