© 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. 48378
    Prev
    Next
    INDEX
    Explanations

    .githubusercontent.com

    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
    gresql
    -0.07
    åĺ±
    -0.07
    semble
    -0.07
    urat
    -0.07
    LEX
    -0.07
    istream
    -0.07
    esda
    -0.07
    วิà¸Ĺย
    -0.07
    è¾¼
    -0.07
    å®īå¸Ĥ
    -0.07
    POSITIVE LOGITS
    åIJīæĸ¯
    0.07
    rek
    0.07
    .com
    0.06
     veille
    0.06
    _W
    0.06
     Fee
    0.06
    .github
    0.06
    Ñĩенко
    0.06
     lá»ĵ
    0.06
    .conf
    0.06
    Activations Density 0.039%

    No Known Activations