© 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. 22873
    Prev
    Next
    INDEX
    Explanations

    biology and related sciences

    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
     calend
    -0.08
     tactical
    -0.08
    éĻ¤æģ¶
    -0.08
     blind
    -0.07
    å½ĵéĿ¢
    -0.07
     Blind
    -0.07
    ophone
    -0.07
     Metall
    -0.07
    oxide
    -0.07
    å®ŀåĬ¡
    -0.07
    POSITIVE LOGITS
    çĶŁçī©
    0.14
     biology
    0.13
     biological
    0.13
    çĶŁçī©åѦ
    0.13
     organisms
    0.13
    çĶŁçī©çļĦ
    0.12
     biologist
    0.12
     organism
    0.12
    çļĦçĶŁçī©
    0.12
     Biology
    0.11
    Activations Density 0.097%

    No Known Activations