© 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. 43182
    Prev
    Next
    INDEX
    Explanations

    maybe

    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
    makes
    -0.29
     passes
    -0.25
    æĿ¥åİĨ
    -0.24
    ãĤĤãģĹ
    -0.24
     simply
    -0.23
     Regular
    -0.23
    ecessarily
    -0.23
     Interpret
    -0.23
     masked
    -0.23
    åĩ¡
    -0.23
    POSITIVE LOGITS
     integrate
    0.42
     distribute
    0.41
     look
    0.38
     terminate
    0.37
     organize
    0.36
     describe
    0.35
     compensate
    0.35
     participate
    0.35
     announce
    0.35
     settle
    0.35
    Activations Density 0.001%

    No Known Activations