© 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. 32421
    Prev
    Next
    INDEX
    Explanations

    end of quote or sentence 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
    ¼Ī
    -0.08
    enson
    -0.07
    igm
    -0.07
     calab
    -0.07
     someday
    -0.07
    ç»İ
    -0.07
    arez
    -0.07
     allegedly
    -0.07
    igi
    -0.07
    åİĭ
    -0.07
    POSITIVE LOGITS
    为æѤ
    0.07
    çī¹æĢ§
    0.07
    éĩįçĤ¹åħ³æ³¨
    0.07
     emphasizing
    0.06
     highlighting
    0.06
    è¿ĻæĦıåij³çĿĢ
    0.06
     implic
    0.06
    åıĪéģĵ
    0.06
    æĦıåij³çĿĢ
    0.06
    γη
    0.06
    Activations Density 0.017%

    No Known Activations