© 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. 13791
    Prev
    Next
    INDEX
    Explanations

    tables, colors, termin, track, behavior, Jack, Search, edges, tail

    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
    oug
    -0.07
     hal
    -0.07
     βο
    -0.07
    uck
    -0.06
    认
    -0.06
    èªį
    -0.06
    æİ¢
    -0.06
    heed
    -0.06
    åĩij
    -0.06
    åĻĮ
    -0.06
    POSITIVE LOGITS
    çĦ¶å¤§
    0.08
    chemas
    0.08
    волÑĮ
    0.08
    åŃ¦å£«
    0.07
    åķ¼
    0.07
    æĹ¥å¸¸å·¥ä½ľ
    0.07
    enhagen
    0.07
     fitte
    0.07
    ivery
    0.07
    -local
    0.07
    Activations Density 0.028%

    No Known Activations