© 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. 23239
    Prev
    Next
    INDEX
    Explanations

    simplify expressions

    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
    çļĦå®ŀéĻħ
    -0.07
    éĵ¡
    -0.07
    åĢ¼çļĦ
    -0.07
    åĢ¼æĺ¯
    -0.07
    çļĦ羣æŃ£
    -0.07
     actually
    -0.06
    æ®ĥ
    -0.06
    åľ¨èº«
    -0.06
    -
    -0.06
    çļĦæīĢæľī
    -0.06
    POSITIVE LOGITS
    oley
    0.08
    ODO
    0.08
    __:
    0.07
    åĴĮè°ĥæķ´
    0.07
    thinkable
    0.07
    å§
    0.07
    kses
    0.07
    rilla
    0.07
    }:
    0.07
    tragen
    0.07
    Activations Density 0.003%

    No Known Activations