© 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. 42926
    Prev
    Next
    INDEX
    Explanations

    say "place"

    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
     locations
    -0.38
     places
    -0.37
    _locations
    -0.36
     Locations
    -0.35
    locations
    -0.35
     lugares
    -0.33
     Places
    -0.31
    Locations
    -0.31
    Places
    -0.30
    .locations
    -0.30
    POSITIVE LOGITS
     o
    0.33
    p
    0.32
     als
    0.31
     p
    0.30
    d
    0.30
     fo
    0.30
     ro
    0.30
     art
    0.28
    ä½ľèĢħæīĢæľī
    0.27
     cp
    0.27
    Activations Density 0.003%

    No Known Activations