© 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. 20257
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
    зал
    -0.09
    hund
    -0.08
    ENDO
    -0.08
    æģ°åĪ°å¥½å¤Ħ
    -0.08
    /www
    -0.08
    DeviceInfo
    -0.07
    olet
    -0.07
    ocard
    -0.07
    EEK
    -0.07
    alfa
    -0.07
    POSITIVE LOGITS
    ä¸įè§ģ
    0.08
    å¿«å¿«
    0.07
    ¶
    0.07
    窿
    0.07
    kop
    0.06
    arken
    0.06
    è¿Ļç§į人
    0.06
    åĬ¡
    0.06
    Âł
    0.06
    adge
    0.06
    Activations Density 0.060%

    No Known Activations