© 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. 19973
    Prev
    Next
    INDEX
    Explanations

    conversations, vitro, standard, Pictures

    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
    ing
    -0.08
    æŃ¢
    -0.07
    uring
    -0.07
    olson
    -0.07
    l
    -0.07
    ks
    -0.07
    1
    -0.07
    å¥ī
    -0.06
    acking
    -0.06
    lt
    -0.06
    POSITIVE LOGITS
    åı¯æ¢¦
    0.10
    人æ°ijåħ±åĴĮåĽ½
    0.09
    åĩĿå¿ĥ
    0.09
    ERRU
    0.09
    ekat
    0.09
    ħĮ
    0.08
    .Sin
    0.08
    åĨĻä½ľä¸ļ
    0.08
    reste
    0.08
    =====
    0.08
    Activations Density 0.012%

    No Known Activations