© 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. 60418
    Prev
    Next
    INDEX
    Explanations

    factors affecting conditions

    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
    rach
    -0.08
    ç©´
    -0.07
    ollection
    -0.07
    åį¿
    -0.07
    WithContext
    -0.07
    ãģĭãģªãģĦ
    -0.07
    é³Į
    -0.07
    çī¹éĩĮ
    -0.07
     amus
    -0.07
    ildo
    -0.06
    POSITIVE LOGITS
    æľīåĪ©äºİ
    0.08
     favors
    0.08
     profitability
    0.08
     favour
    0.08
    ye
    0.08
     favourable
    0.08
     favorable
    0.08
    è¶Ĭæĥ³
    0.08
     sensible
    0.07
     favoured
    0.07
    Activations Density 0.003%

    No Known Activations