© 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. 45237
    Prev
    Next
    INDEX
    Explanations

    acceptable limits

    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
    faat
    -0.08
    æ¯ĶåĪĨ
    -0.07
    anut
    -0.07
     laps
    -0.07
     Hib
    -0.06
    aszt
    -0.06
    antz
    -0.06
    procs
    -0.06
    è¿ĺ羣çļĦ
    -0.06
    örd
    -0.06
    POSITIVE LOGITS
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.17
    ä¸įèĥ½è¶ħè¿ĩ
    0.13
     allowable
    0.13
     acceptable
    0.13
    ä¸įè¶ħè¿ĩ
    0.13
     permissible
    0.12
    éĻIJåĪ¶
    0.12
     limits
    0.12
    éĻIJåĪ¶çļĦ
    0.11
     Limits
    0.11
    Activations Density 0.063%

    No Known Activations