© 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. 25221
    Prev
    Next
    INDEX
    Explanations

    max limits

    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
    afb
    -0.07
     Hubb
    -0.07
    валÑĮ
    -0.07
    è¦ıç´Ħ
    -0.07
    干湿
    -0.07
    个åŁİå¸Ĥ
    -0.07
    人ä½ĵ
    -0.06
    è¿ĻæĬĬ
    -0.06
    hiba
    -0.06
    ä¹¾åĿ¤
    -0.06
    POSITIVE LOGITS
    åĪ»
    0.07
    åĨħå®¹è¿Ľè¡Į
    0.07
     verbosity
    0.07
    udy
    0.07
     Unlimited
    0.07
    æĹłæŃ¢å¢ĥ
    0.07
     unlimited
    0.07
    èĭ¦
    0.06
    dia
    0.06
    undle
    0.06
    Activations Density 0.010%

    No Known Activations