© 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. 30942
    Prev
    Next
    INDEX
    Explanations

    zero-based

    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
    lern
    -0.10
    à¸Ļà¹īà¸Ńย
    -0.09
    hape
    -0.09
    ebes
    -0.09
    jenigen
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    nesia
    -0.09
    تابعة
    -0.09
    hift
    -0.09
    ALTH
    -0.08
    POSITIVE LOGITS
    ish
    0.11
    ed
    0.09
    /null
    0.08
    lymp
    0.08
    åľ¨
    0.08
    ption
    0.08
    -ish
    0.07
    ing
    0.07
    ç¼¥ç¼Ī
    0.07
    ism
    0.07
    Activations Density 0.014%

    No Known Activations