© 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. 48905
    Prev
    Next
    INDEX
    Explanations

    non-zero

    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
    ells
    -0.08
    以德
    -0.07
    s
    -0.06
     lẫn
    -0.06
    çļĦæĸ¹æ³ķæĺ¯
    -0.06
    пой
    -0.06
    annels
    -0.06
    INGS
    -0.06
    WAYS
    -0.06
    ércoles
    -0.06
    POSITIVE LOGITS
    ivial
    0.09
    ãĢħ
    0.09
    çĦ¶å¤§
    0.08
    ุม
    0.08
    å¢Ĵ
    0.08
    ór
    0.07
    çĥĪ
    0.07
    æģĴ
    0.07
    TTY
    0.07
    isky
    0.07
    Activations Density 0.006%

    No Known Activations