© 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. 57312
    Prev
    Next
    INDEX
    Explanations

    subject to or policy

    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
    åı¸
    -0.07
    æĬķèµĦä»·åĢ¼
    -0.07
    æľīä¸Ģ次
    -0.07
     nho
    -0.07
    sla
    -0.06
    æºľæºľ
    -0.06
    osas
    -0.06
    ÃŃlico
    -0.06
    éĥ¨å°±
    -0.06
     Jep
    -0.06
    POSITIVE LOGITS
     catch
    0.07
    绵延
    0.07
    æ°¸å®ļ
    0.07
    ä»İ严治
    0.07
    lander
    0.06
    mit
    0.06
    è¦ı模
    0.06
    uchy
    0.06
    éĻIJæľŁ
    0.06
    à¸ģล
    0.06
    Activations Density 0.034%

    No Known Activations