© 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. 43116
    Prev
    Next
    INDEX
    Explanations

    administrative positions

    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
     nextState
    -0.27
    wij
    -0.25
    .trip
    -0.24
    åı¤ãģĦ
    -0.24
    æĸĩåĮĸåºķèķ´
    -0.24
    ·¸
    -0.24
     moderated
    -0.24
     currentState
    -0.23
     plaats
    -0.23
    ersed
    -0.23
    POSITIVE LOGITS
    atas
    0.30
    æ°´åĪĨ
    0.29
     spelled
    0.28
     conserv
    0.27
    ä½IJ
    0.26
    èĮĥ
    0.26
     dy
    0.26
    .dy
    0.26
     Markets
    0.26
     Conserv
    0.25
    Activations Density 0.009%

    No Known Activations