© 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. 11590
    Prev
    Next
    INDEX
    Explanations

    option a

    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
    And
    -0.07
    tiv
    -0.07
    finder
    -0.06
    ä»Ģä¹ĪéĹ®é¢ĺ
    -0.06
    ä¹ĭæľ¬
    -0.06
    _iv
    -0.06
    æ£ĺ
    -0.06
    lef
    -0.06
     Gunn
    -0.06
     caer
    -0.06
    POSITIVE LOGITS
    edan
    0.08
    éĢī项
    0.07
     référenc
    0.07
    одно
    0.07
    åįķéĢīé¢ĺ
    0.07
    å±ı
    0.07
    åĪĽæĬķ
    0.07
    ãģĹãĤĤ
    0.06
    juÄį
    0.06
    iseau
    0.06
    Activations Density 0.008%

    No Known Activations