© 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. 39448
    Prev
    Next
    INDEX
    Explanations

    numbers or symbols

    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
    _wo
    -0.07
    öl
    -0.07
    rano
    -0.07
    chw
    -0.07
    æĪĺçģ«
    -0.07
    erd
    -0.07
    å±¥èģĮ尽责
    -0.07
    Aw
    -0.06
    足äºĨ
    -0.06
    ç»ĻæĪij们çļĦ
    -0.06
    POSITIVE LOGITS
     possible
    0.08
    åı¯èĥ½çļĦ
    0.07
    possible
    0.07
    Possible
    0.07
    mail
    0.07
    åīĶéĢı
    0.07
    anger
    0.06
    imana
    0.06
     Possible
    0.06
     possibly
    0.06
    Activations Density 0.019%

    No Known Activations