© 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. 29380
    Prev
    Next
    INDEX
    Explanations

    options to continue

    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
    èµĶåģ¿è´£ä»»
    -0.08
    å½ĵ羣
    -0.07
     getCategory
    -0.07
    ä¸įä½ıçļĦ
    -0.06
    æīĢ使çĶ¨çļĦ
    -0.06
     underlying
    -0.06
    коÑĤа
    -0.06
     poca
    -0.06
    esos
    -0.06
    ounter
    -0.06
    POSITIVE LOGITS
    继ç»Ń
    0.10
    åı¯ä»¥ç»§ç»Ń
    0.09
     Options
    0.08
    ä¼ĺåħĪ
    0.08
    éĢīæĭ©
    0.08
    continue
    0.08
    继ç»Ńè¿Ľè¡Į
    0.08
    ä¸ĭä¸ĢæŃ¥
    0.08
    ither
    0.08
     options
    0.08
    Activations Density 0.010%

    No Known Activations