© 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. 29946
    Prev
    Next
    INDEX
    Explanations

    proofs with ratios and permutations

    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
    emean
    -0.08
    spur
    -0.07
    bucks
    -0.07
    丹çĶ°
    -0.07
    /plugins
    -0.06
    åŁŁçļĦ
    -0.06
    çłº
    -0.06
    geld
    -0.06
    èĽĩ
    -0.06
    ä¸ĩåħ¬éĩĮ
    -0.06
    POSITIVE LOGITS
     ratios
    0.08
    ç»Ŀ伦
    0.08
     huge
    0.07
    roid
    0.07
     ratio
    0.07
    Ïģγ
    0.07
    ä¹ĭ大
    0.07
    巨大çļĦ
    0.07
    æł¸æ¡ĥ
    0.07
     numbers
    0.07
    Activations Density 0.006%

    No Known Activations