© 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. 9827
    Prev
    Next
    INDEX
    Explanations

    family and inheritance

    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
     dimensional
    -0.08
    wb
    -0.08
    æŀģèĩ´
    -0.08
    atan
    -0.08
    èĨĺ
    -0.07
    ije
    -0.07
    涨
    -0.07
    ,dim
    -0.07
    太çĻ½
    -0.07
    _dims
    -0.07
    POSITIVE LOGITS
    ä¸ī代
    0.12
    éģĹä¼ł
    0.11
    çĽ´ç³»
    0.11
     pedigree
    0.10
     inheritance
    0.10
     recurrence
    0.09
     pedig
    0.09
    ç¶Ļ
    0.09
     genetic
    0.09
     familial
    0.09
    Activations Density 0.053%

    No Known Activations