© 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. 48216
    Prev
    Next
    INDEX
    Explanations

    objects and nouns

    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
    ìa
    -0.07
    ä¸įæĺİçļĦ
    -0.07
    æĺ¯ä¸Ģå¹´
    -0.07
    ä»ĺæ¸ħ
    -0.07
    å¼ıçļĦ
    -0.07
    çľĭ好çļĦ
    -0.07
    åİĭæľº
    -0.07
    undle
    -0.06
    çļĦ姿åĬ¿
    -0.06
    Spo
    -0.06
    POSITIVE LOGITS
    -toggle
    0.07
    ä¸İéĿŀ
    0.07
    gens
    0.07
    orando
    0.07
    leden
    0.07
    æħİçĶ¨
    0.07
    mates
    0.07
     disproportionately
    0.06
    ä¸İæĻ®éĢļ
    0.06
    åįłæ¯Ķ
    0.06
    Activations Density 0.439%

    No Known Activations