© 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. 29625
    Prev
    Next
    INDEX
    Explanations

    Holy Spirit

    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
    inski
    -0.07
    zin
    -0.07
    è¼
    -0.07
    zkod
    -0.07
    çĶ¨æĸĻ
    -0.07
    itäten
    -0.07
    änn
    -0.06
    ÑĢоб
    -0.06
    ibrary
    -0.06
    izens
    -0.06
    POSITIVE LOGITS
    åľ£çģµ
    0.09
    åĬ©
    0.08
     Burnett
    0.08
     Spirit
    0.08
     Pent
    0.08
     souffle
    0.08
    -filled
    0.07
    ä¹ĭæ°Ķ
    0.07
    åĬ©ä½ł
    0.07
    çļĦæ°Ķæģ¯
    0.07
    Activations Density 0.009%

    No Known Activations