© 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. 49113
    Prev
    Next
    INDEX
    Explanations

    microsatellite repeats Sequences STR expansion

    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
    æīĵéĴĪ
    -0.07
    æ§Ľ
    -0.07
    agas
    -0.07
    çļĦä¸Ģå¼ł
    -0.07
    ä¸į误
    -0.07
    å·¥ä½ľå²Ĺä½į
    -0.07
    ril
    -0.07
    lag
    -0.07
     Semb
    -0.06
    cepts
    -0.06
    POSITIVE LOGITS
    段
    0.09
    è¿Ļ段
    0.09
    segment
    0.09
    Segment
    0.08
     segment
    0.08
     repeats
    0.08
    ä¸Ģ段
    0.08
    段èIJ½
    0.08
    ãĥªãĥĶ
    0.08
     expansions
    0.08
    Activations Density 0.029%

    No Known Activations