© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20297
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and codes (AD, AM, COM)

    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
    èŤ
    -0.07
    代
    -0.06
    apia
    -0.06
    ago
    -0.06
     cel
    -0.06
    ÃŃce
    -0.06
     CEL
    -0.06
     lume
    -0.06
    orts
    -0.06
    acu
    -0.06
    POSITIVE LOGITS
    æĸĽ
    0.08
    ilden
    0.08
    deal
    0.08
    好åķĬ
    0.08
    sius
    0.07
    éĥ½æĺ¯èĩªå·±
    0.07
    EMBER
    0.07
    ermen
    0.07
    ìľłìĿĺ
    0.07
    OUS
    0.07
    Activations Density 0.004%

    No Known Activations