© 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. 17981
    Prev
    Next
    INDEX
    Explanations

    æ and chemical elements

    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
    åħ¶éģĵ
    -0.07
    ÏĢÏģα
    -0.07
    θει
    -0.07
    wij
    -0.07
    大éģĵ
    -0.07
     ÐIJпÑĢе
    -0.07
    西çľģ
    -0.07
    _COMPARE
    -0.07
     \@
    -0.07
    žd
    -0.07
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.08
    åıĬåħ¶ä»ĸ
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.08
     or
    0.07
    缸åħ³åĨħ容
    0.07
    /o
    0.07
    åħĭæĸ¯
    0.07
    缸åħ³çļĦåĨħ容
    0.07
    ãģ²
    0.07
    ãĤĦ
    0.06
    Activations Density 0.129%

    No Known Activations