© 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. 1129
    Prev
    Next
    INDEX
    Explanations

    HTML entities and escape characters

    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
    Äįet
    -0.08
    erie
    -0.08
    alez
    -0.07
    алÑĥ
    -0.07
    umerator
    -0.07
    ledge
    -0.07
    leit
    -0.06
    æĻĤè¨Ī
    -0.06
    linger
    -0.06
    à®ŀ
    -0.06
    POSITIVE LOGITS
    ÙĨÙĬÙĨ
    0.09
    羣çĪ±
    0.08
    ÙĪس
    0.07
    ÑĤÑģÑı
    0.07
    缸å½ĵ
    0.07
    سط
    0.07
    .echo
    0.06
    _demo
    0.06
    ä¸ĢéĹª
    0.06
    ÙĨØ©
    0.06
    Activations Density 0.018%

    No Known Activations