© 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. 23143
    Prev
    Next
    INDEX
    Explanations

    type B or version

    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
    缨
    -0.07
    åıĺæĢ§
    -0.07
    olas
    -0.07
    ters
    -0.07
    çīµ
    -0.06
    åķĨä¸ļçĶ¨éĢĶ
    -0.06
     Äijun
    -0.06
    被æīĵ
    -0.06
    æݨ翻
    -0.06
    æĭ¿æĿ¥
    -0.06
    POSITIVE LOGITS
    æŀĹ家
    0.08
     nearby
    0.08
    .dir
    0.08
    è¿ľæµģ
    0.07
    ä¹¾çĩ¥
    0.07
    faq
    0.07
     Spot
    0.07
    IDL
    0.07
    ç»ķè¡Į
    0.07
    æī¾åĪ°èĩªå·±
    0.07
    Activations Density 0.001%

    No Known Activations