© 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. 28349
    Prev
    Next
    INDEX
    Explanations

    name $ " 0 glory _series ease name long

    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
    åIJİèĢħ
    -0.07
    ilé
    -0.06
    angelog
    -0.06
    .docs
    -0.06
    æľī没æľī
    -0.06
    apur
    -0.06
    il
    -0.06
    è¿ĩä¸įåİ»
    -0.06
    缴æݥ被
    -0.06
    åĺĽ
    -0.06
    POSITIVE LOGITS
     petró
    0.08
     serviceName
    0.08
    äºĶé¢ľåħŃèī²çļĦ
    0.08
    )&&(
    0.08
    åĬłåħ¥æĶ¶èĹı
    0.08
    */)
    0.08
    çļĦ人æĿ¥è¯´
    0.07
    ลà¸ĩà¹ĥà¸Ļ
    0.07
    ä¹ĭæĹ¥èµ·
    0.07
    estroy
    0.07
    Activations Density 0.002%

    No Known Activations