© 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. 55388
    Prev
    Next
    INDEX
    Explanations

    running Python code or scripts

    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
    .Round
    -0.06
    åĴ
    -0.06
     Bov
    -0.06
    æĥ¹
    -0.06
    ç»į
    -0.06
    _BEGIN
    -0.06
    å¤ĸåªĴ
    -0.06
     acaso
    -0.06
    æ©
    -0.06
    iley
    -0.06
    POSITIVE LOGITS
    Python
    0.09
    Pid
    0.08
    ادÙĩ
    0.08
    оÑģÑĤа
    0.08
    bilt
    0.08
    TPL
    0.07
    Messenger
    0.07
    öst
    0.07
     Python
    0.07
    aminer
    0.07
    Activations Density 0.005%

    No Known Activations