© 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. 46683
    Prev
    Next
    INDEX
    Explanations

    python def create

    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
    cking
    -0.07
    á»ĥn
    -0.07
    cak
    -0.06
    åĮħ袱
    -0.06
    ers
    -0.06
    uada
    -0.06
    lings
    -0.06
    opup
    -0.06
    åı¯ä»¥æł¹æį®èĩªå·±çļĦ
    -0.06
    活泼
    -0.06
    POSITIVE LOGITS
    ÑĩаÑĤки
    0.07
    intér
    0.07
    WD
    0.07
     Leng
    0.07
    -rest
    0.07
    è¿ĶåĽŀåĪĹ表
    0.06
    äst
    0.06
    -tools
    0.06
     numeros
    0.06
    gé
    0.06
    Activations Density 0.005%

    No Known Activations