© 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. 43844
    Prev
    Next
    INDEX
    Explanations

    of

    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
    迳
    -0.28
    ONGL
    -0.27
    çļĦéĤ£ä¸ª
    -0.26
    ⣵
    -0.26
    Ñħи
    -0.25
     MOT
    -0.23
    æĿ²
    -0.23
    åģĥ
    -0.23
    -back
    -0.23
    vely
    -0.23
    POSITIVE LOGITS
     your
    0.38
    your
    0.35
    æĤ¨çļĦ
    0.33
    Your
    0.32
    -your
    0.30
    ä½łçļĦ
    0.30
     Your
    0.29
     ваÑĪ
    0.29
    æľĢåIJİä¸Ģ
    0.29
     idea
    0.27
    Activations Density 0.000%

    No Known Activations