© 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. 57744
    Prev
    Next
    INDEX
    Explanations

    Texas Government

    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
    æµ·æ£ł
    -0.07
    å·¥ç¨ĭæĬĢæľ¯
    -0.07
    tgt
    -0.07
    amel
    -0.07
    enheim
    -0.07
    .exists
    -0.07
    åħĥèĩ³
    -0.07
    ìĭľìĬ¤
    -0.06
    اطر
    -0.06
    fahren
    -0.06
    POSITIVE LOGITS
    à¹Į
    0.09
    ÑĤÑģÑı
    0.07
    à¸Ļà¹Į
    0.07
    trup
    0.07
    ÙĦÙĪ
    0.07
    sweise
    0.07
    å°Ĭ
    0.06
    ä½Ļ
    0.06
     sund
    0.06
    à¸ĵà¹Į
    0.06
    Activations Density 0.099%

    No Known Activations