© 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. 18843
    Prev
    Next
    INDEX
    Explanations

    originally catered

    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
    mute
    -0.07
    im
    -0.07
    ogi
    -0.07
     ('\
    -0.07
    渡
    -0.06
    bamos
    -0.06
     диÑģÑĤ
    -0.06
    رداد
    -0.06
    ä¸ĭåIJĮ
    -0.06
    佬
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.11
    ä»Ģä¹Ī
    0.08
    åĴĮåIJİ
    0.07
    çģĮ
    0.07
    _),
    0.07
    ä»Ģä¹Īä¸ľè¥¿
    0.07
    以ä¸ĭæĿ¡ä»¶
    0.07
    lette
    0.07
    éĿłå±±
    0.07
    ä»Ģä¹Īæł·
    0.06
    Activations Density 0.004%

    No Known Activations