© 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. 20540
    Prev
    Next
    INDEX
    Explanations

    brown color, hair, sugar, or animal descriptions

    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
    ãģ£ãģ±
    -0.09
    полни
    -0.09
    orious
    -0.09
    FINITY
    -0.09
    tle
    -0.08
    ï¸İ
    -0.08
    Ñĩко
    -0.08
    acon
    -0.08
    èļ£
    -0.08
    uny
    -0.08
    POSITIVE LOGITS
    /black
    0.09
    iers
    0.08
    éis
    0.08
     اÙĦÙĦÙĪÙĨ
    0.07
    ish
    0.07
    ekl
    0.07
    esco
    0.07
    essian
    0.07
    /red
    0.07
    ãģĺãĤģãģ¦
    0.07
    Activations Density 0.055%

    No Known Activations