© 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. 32618
    Prev
    Next
    INDEX
    Explanations

    mathematical and legal clauses

    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
    theit
    -0.07
    åħ¨éĿ¢å»ºè®¾
    -0.07
    iche
    -0.07
    oui
    -0.07
    Õ
    -0.07
    ÑĢоÑı
    -0.07
    бини
    -0.07
    oria
    -0.07
    åħŃä¸ĢåĦ¿ç«¥èĬĤ
    -0.07
    desk
    -0.07
    POSITIVE LOGITS
    Ùħا
    0.07
    acci
    0.07
    ড়
    0.07
    éĻ¢
    0.07
    olt
    0.07
    çĶ³
    0.07
    èĩ£
    0.06
    æĺĨ
    0.06
    á»±c
    0.06
    æķ¦
    0.06
    Activations Density 0.420%

    No Known Activations