© 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. 31753
    Prev
    Next
    INDEX
    Explanations

    PDF page structures

    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
    æľīåħ³äºĭ项
    -0.08
    ØŃاÙħ
    -0.08
    atron
    -0.08
    Å©
    -0.08
    æĭľ
    -0.08
    ascade
    -0.08
    ÙĪتÙĬ
    -0.08
    atian
    -0.08
     Ñģала
    -0.08
    assed
    -0.08
    POSITIVE LOGITS
    æĺ¯åIJĹ
    0.07
    0.06
    OP
    0.06
    æĺ¯åIJ§
    0.06
    ç¥Ŀç¦ıä½ł
    0.06
     constr
    0.06
    两å±Ĥ
    0.06
    icara
    0.06
    éĥ¨éķ¿
    0.06
    2
    0.05
    Activations Density 0.002%

    No Known Activations