© 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. 27-TRANSCODER-HP
    7. 57869
    Prev
    Next
    INDEX
    Explanations

    technical, specific/medical/scientific themes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    instead
    -0.34
     instead
    -0.33
    ä»£æĽ¿
    -0.28
    Instead
    -0.27
     Instead
    -0.26
    -tier
    -0.25
    okin
    -0.25
    满足
    -0.25
    incare
    -0.25
     tai
    -0.25
    POSITIVE LOGITS
    associ
    0.28
    ANEL
    0.28
    æľªæĪIJå¹´
    0.26
    ä¸įå®ī
    0.25
    ä¸įåı¯æĢĿè®®
    0.25
     stressed
    0.25
    пан
    0.24
     efficient
    0.24
     elected
    0.24
    Du
    0.24
    Activations Density 0.000%

    No Known Activations