© 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. 62336
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
    iby
    -0.08
    tuv
    -0.07
    udre
    -0.07
    ongyang
    -0.07
    leases
    -0.07
     Cousins
    -0.07
    ubs
    -0.07
    iki
    -0.07
    ä¸ĭæľī
    -0.07
    ENDOR
    -0.07
    POSITIVE LOGITS
    ç©Ĩ
    0.06
    ulait
    0.06
    è¯ij为
    0.06
    ç½®
    0.06
    èµ°åĬ¨
    0.06
    ä¸Ģæ¡Ī
    0.06
    å¿ĥæĥħ
    0.06
    åīį款
    0.05
     gen
    0.05
    éħ¸è¾£
    0.05
    Activations Density 0.002%

    No Known Activations