© 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. 49153
    Prev
    Next
    INDEX
    Explanations

    file path markers

    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
    estino
    -0.07
    æī¾ä»ĸ
    -0.07
    ¢
    -0.07
    ¡
    -0.06
    igno
    -0.06
    ова
    -0.06
    è¿ŀæİ¥æľī
    -0.06
    ä¸įèĥ½åľ¨
    -0.06
    èģĶç³»çļĦ
    -0.06
    £
    -0.06
    POSITIVE LOGITS
    reat
    0.07
    aml
    0.07
    豪æĿ°
    0.07
    obat
    0.07
    æľºæŀĦæĶ¹éĿ©
    0.07
    змо
    0.07
    è¢Ħ
    0.06
    ä¸ĭåİ»äºĨ
    0.06
    å«£
    0.06
    inet
    0.06
    Activations Density 0.001%

    No Known Activations