© 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. 22108
    Prev
    Next
    INDEX
    Explanations

    code correctness

    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
    æŃ¥
    -0.07
     Dow
    -0.06
    rough
    -0.06
    æĭĻ
    -0.06
    ByUrl
    -0.06
    ä»ĸå¾Ī
    -0.06
    è°£
    -0.06
    ÃŃz
    -0.06
    æĿ¥è¡¨ç¤º
    -0.06
    æĪIJ为ä¸Ģ个
    -0.06
    POSITIVE LOGITS
    æīįåıijçİ°
    0.08
    åıijçİ°æľī
    0.08
    utenberg
    0.08
    missions
    0.07
    ranges
    0.07
    itsu
    0.07
    缮æłĩä»»åĬ¡
    0.07
    åĨįä¸ī
    0.07
    çŁŃçŁŃçļĦ
    0.07
    ITS
    0.07
    Activations Density 0.013%

    No Known Activations