© 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. 3335
    Prev
    Next
    INDEX
    Explanations

    asking about

    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
    alde
    -0.07
    IGO
    -0.07
     Porr
    -0.06
    äºĮåįĥ
    -0.06
    ä¹İ
    -0.06
     Essentially
    -0.06
    主è¦ģä»İ
    -0.06
     libur
    -0.06
    Decre
    -0.06
    ---</
    -0.06
    POSITIVE LOGITS
    ĽĦ
    0.08
    าà¸ģร
    0.08
    pek
    0.08
    urg
    0.07
    å°±æĺ¯è¦ģ
    0.07
    vard
    0.07
    é»
    0.07
     trắc
    0.07
    nad
    0.07
    akh
    0.07
    Activations Density 0.001%

    No Known Activations