© 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. 56959
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    uer
    -0.08
    toria
    -0.08
    aat
    -0.08
    uum
    -0.08
    óc
    -0.07
    ié
    -0.07
    ing
    -0.07
    aic
    -0.07
    udu
    -0.07
    oureuse
    -0.07
    POSITIVE LOGITS
    æķħèĢĮ
    0.07
    tran
    0.07
    apl
    0.07
    ë¦Ħ
    0.06
    ä¸Ģ个åı«
    0.06
    wend
    0.06
    ths
    0.06
    нÑĭй
    0.06
    ahrungs
    0.06
    ments
    0.06
    Activations Density 0.001%

    No Known Activations