© 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. 9334
    Prev
    Next
    INDEX
    Explanations

    Random, diverse content

    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
     wind
    -0.26
    =cut
    -0.26
     craft
    -0.25
    ä¸į让
    -0.25
    oga
    -0.25
    acam
    -0.25
    [child
    -0.24
    åıįæĺł
    -0.24
    ounder
    -0.24
     crafts
    -0.24
    POSITIVE LOGITS
    è¿ĻéĩĮæĺ¯
    0.29
     Welcome
    0.29
    Welcome
    0.28
    æľ¬ç½ij
    0.28
    è¿ĻéĩĮçļĦ
    0.27
    Clinical
    0.26
    CUS
    0.26
    Commercial
    0.26
     Core
    0.26
    cus
    0.26
    Activations Density 0.052%

    No Known Activations