© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64187
    Prev
    Next
    INDEX
    Explanations

    apress

    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
    ource
    -0.09
    sev
    -0.08
    aland
    -0.08
    lor
    -0.08
    主ä½ĵå·¥ç¨ĭ
    -0.08
    ÏĨÎŃ
    -0.07
    mour
    -0.07
    oftware
    -0.07
    æľ¬å¸ĸ
    -0.07
    ä¸Ńé¤IJ
    -0.07
    POSITIVE LOGITS
    éĿ¢åŃIJ
    0.07
    bam
    0.07
     impression
    0.06
    åį°è±¡
    0.06
    ird
    0.06
    åıijå¸ĥåħ¬åijĬ
    0.06
    æīĩ
    0.06
    ahuan
    0.06
    og
    0.06
    æłĩ
    0.05
    Activations Density 1.326%

    No Known Activations