© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30323
    Prev
    Next
    INDEX
    Explanations

    graph, chart, world, int

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —but
    -0.08
    thane
    -0.08
    ÑħÑĸ
    -0.07
    дей
    -0.07
    ÑĸÑĢ
    -0.07
     Krem
    -0.07
    поÑĩ
    -0.07
    è¿ĻéĩĮæľī
    -0.07
    Ïĩε
    -0.07
    uros
    -0.07
    POSITIVE LOGITS
     Du
    0.08
    çļĦé¦ĸè¦ģ
    0.07
    设å¤ĩå®īè£ħ
    0.07
    inst
    0.07
    Du
    0.07
    ADI
    0.06
     zat
    0.06
     Fid
    0.06
    åIJĽ
    0.06
    ora
    0.06
    Activations Density 0.002%

    No Known Activations