© 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. 39134
    Prev
    Next
    INDEX
    Explanations

    part of, half of, finally

    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
    iken
    -0.06
    ......
    -0.06
    åĴĮæĤ¨
    -0.06
    -0.06
    æŃ£ç¡®
    -0.06
    Ñģи
    -0.06
     redis
    -0.06
    ç¦ıç¦Ħ
    -0.05
    .generated
    -0.05
    lish
    -0.05
    POSITIVE LOGITS
    æĺ¯åĽ½åĨħ
    0.08
    jav
    0.08
    akis
    0.08
    enje
    0.08
    éĹ®é¢ĺæĺ¯
    0.08
    ìŀIJìĿ¸
    0.08
    adoo
    0.08
    azzo
    0.07
    .sap
    0.07
    uccio
    0.07
    Activations Density 0.002%

    No Known Activations