© 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. 2390
    Prev
    Next
    INDEX
    Explanations

    chr(number) or chr(hex)

    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
    å£Į
    -0.07
    lais
    -0.07
    illy
    -0.07
    æ±İ
    -0.07
     appropriated
    -0.07
    bij
    -0.07
    ¯
    -0.07
    iable
    -0.07
    积
    -0.07
    ç¯Ļ
    -0.07
    POSITIVE LOGITS
    uned
    0.10
    ptica
    0.07
    éĢIJ
    0.07
    彪
    0.07
    ArrayOf
    0.07
    Picker
    0.07
    رÙĪج
    0.07
    å¥Ķ
    0.06
    çĨ
    0.06
    akup
    0.06
    Activations Density 0.030%

    No Known Activations