© 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. 42483
    Prev
    Next
    INDEX
    Explanations

    technical/medical

    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
    iram
    -0.29
    TH
    -0.29
    runner
    -0.27
    éĿ¢ä¸Ĭ
    -0.27
    笼
    -0.27
    еÑĢи
    -0.26
    inke
    -0.25
    agem
    -0.25
    æijĬ
    -0.25
    WW
    -0.25
    POSITIVE LOGITS
    glas
    0.28
    转æį¢
    0.27
    chluss
    0.26
    说ä¸įåĩº
    0.25
    lesi
    0.24
    ied
    0.24
     dead
    0.24
    å¾®åŀĭ
    0.24
    dead
    0.24
    letal
    0.24
    Activations Density 0.002%

    No Known Activations