© 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. 23705
    Prev
    Next
    INDEX
    Explanations

    company, mortgage, defendant, bank

    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
    强éĻ©
    -0.07
    ä½łè¦ģæĺ¯
    -0.06
    èĺĭ
    -0.06
     R
    -0.06
     (
    -0.06
    æ³¢
    -0.06
     Allison
    -0.06
     w
    -0.06
    éĵº
    -0.06
     ATS
    -0.06
    POSITIVE LOGITS
    缴æİ¥åIJij
    0.09
    èµĦæĸĻæĺ¾ç¤º
    0.09
    evin
    0.09
    çļĦåħ·ä½ĵæĥħåĨµ
    0.09
    _CAPACITY
    0.09
    ä¸Ģ个å¤ļæľĪ
    0.09
    æ¶īæ¡Ī
    0.08
    uvi
    0.08
    ĩ
    0.08
    oteca
    0.08
    Activations Density 0.004%

    No Known Activations