© 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. 14803
    Prev
    Next
    INDEX
    Explanations

    poetic forms like rhyme and haiku

    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
    rops
    -0.08
    ynet
    -0.08
    inja
    -0.08
    ropa
    -0.08
    ernal
    -0.08
     Schönh
    -0.08
    thood
    -0.07
    åĨ°éĽª
    -0.07
    oni
    -0.07
    valu
    -0.07
    POSITIVE LOGITS
     rhythm
    0.11
    飵å¾ĭ
    0.11
     rhyth
    0.10
    å·¥æķ´
    0.10
    çļĦèĬĤå¥ı
    0.09
     poetry
    0.09
     ÑĢиÑĤ
    0.09
    æķ´é½IJ
    0.08
     poetic
    0.08
    æİĴåĪĹ
    0.08
    Activations Density 0.007%

    No Known Activations