© 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. 27726
    Prev
    Next
    INDEX
    Explanations

    direction and extent

    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
     transitional
    -0.08
     intimately
    -0.08
    è¿ĩ渡
    -0.08
    é«ĺ级
    -0.07
     Transitional
    -0.07
     дели
    -0.07
    artial
    -0.07
    perimental
    -0.07
    åįĥ家
    -0.07
    æģª
    -0.07
    POSITIVE LOGITS
    æĹłç©·
    0.13
     limitless
    0.13
     infinite
    0.13
     unlimited
    0.13
     infinity
    0.13
    æĹłéĻIJçļĦ
    0.12
     Unlimited
    0.12
    æĹłæŃ¢
    0.11
    å¢ŀéķ¿çļĦ
    0.11
     runaway
    0.11
    Activations Density 0.048%

    No Known Activations