© 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. 24242
    Prev
    Next
    INDEX
    Explanations

    subscribe, follow, connect

    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
    èģĶç³»åķĨ家
    -0.07
    ç½ijåıĭä¸Ĭä¼ł
    -0.07
    éĻ¤
    -0.07
    åıĹæīĺ
    -0.06
    为æĤ¨ä»ĭç»į
    -0.06
     certain
    -0.06
    heimer
    -0.06
    æīĢ以éľĢè¦ģ
    -0.06
     border
    -0.06
    ãģ¾ãģ§ãģ¯
    -0.06
    POSITIVE LOGITS
    ilian
    0.09
    对æĪij们çļĦ
    0.09
    对æĪijçļĦ
    0.08
    immat
    0.08
    assen
    0.08
    ÑģиÑı
    0.08
    stalk
    0.08
    对æĪij们
    0.08
    æĪij们çļĦ
    0.08
    ptica
    0.08
    Activations Density 0.573%

    No Known Activations