© 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. 43760
    Prev
    Next
    INDEX
    Explanations

    human

    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
    人类
    -0.30
    ngr
    -0.29
    safe
    -0.29
    Human
    -0.28
     safest
    -0.28
    sky
    -0.28
    human
    -0.27
    ses
    -0.27
    sse
    -0.27
     human
    -0.27
    POSITIVE LOGITS
     being
    0.77
    being
    0.71
    Being
    0.65
     Being
    0.60
    -being
    0.48
     sendo
    0.39
     siendo
    0.37
    ly
    0.36
     essere
    0.36
     étant
    0.36
    Activations Density 0.012%

    No Known Activations