© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56060
    Prev
    Next
    INDEX
    Explanations

    section or boundary

    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
    çĶļèĩ³æ¯Ķ
    -0.07
     uniformly
    -0.07
    åĢ¼
    -0.07
    åĢ¼çļĦ
    -0.07
    uniform
    -0.07
    /vendors
    -0.07
    åIJĮæŃ¥
    -0.07
    vÃŃo
    -0.07
    è¶ħ
    -0.07
    _GENERIC
    -0.07
    POSITIVE LOGITS
     incid
    0.08
     formed
    0.07
     requested
    0.07
    æľī两个
    0.07
    utzen
    0.07
     inciden
    0.07
     intersect
    0.07
    tert
    0.07
    Requested
    0.07
    è¿Ļ两个
    0.07
    Activations Density 0.002%

    No Known Activations