© 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. 32654
    Prev
    Next
    INDEX
    Explanations

    function

    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
    忽
    -0.08
    áo
    -0.07
    è¾ĵåįµ
    -0.07
     Brescia
    -0.06
     cord
    -0.06
    æłĩåĩĨè¦ģæ±Ĥ
    -0.06
     barb
    -0.06
     numbers
    -0.06
     bufsize
    -0.06
    åªĽ
    -0.06
    POSITIVE LOGITS
     functional
    0.08
     functions
    0.08
     Functional
    0.07
    ève
    0.07
     funcs
    0.07
    functional
    0.07
    ัà¸ĩà¸ģ
    0.07
     Functions
    0.07
    funktionen
    0.07
    .func
    0.07
    Activations Density 0.001%

    No Known Activations