© 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. 48824
    Prev
    Next
    INDEX
    Explanations

    clauses and provisions

    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
    upun
    -0.08
    -cols
    -0.08
    æĦŁåĻ¨
    -0.07
    ä¼ģä¸ļåħ¬ç¤º
    -0.07
    _ASSOC
    -0.07
     Legislat
    -0.07
     Raleigh
    -0.07
    ç«ĭæ¡Īä¿¡æģ¯
    -0.06
    èµ°é«ĺ
    -0.06
    reten
    -0.06
    POSITIVE LOGITS
    æĿ¡æ¬¾
    0.16
     clauses
    0.16
     clause
    0.14
     provisions
    0.12
    Clause
    0.11
    clause
    0.11
     cláus
    0.11
     Clause
    0.10
    åĨĻæĺİ
    0.10
     wording
    0.10
    Activations Density 0.046%

    No Known Activations