© 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. 45722
    Prev
    Next
    INDEX
    Explanations

    unique valid inputs

    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
    ä¸įèĥľ
    -0.07
    驳
    -0.07
    éĻĮçĶŁ
    -0.07
    æ¡ĮéĿ¢ä¸Ĭ
    -0.07
    enburg
    -0.07
     Retrou
    -0.07
    ceu
    -0.07
    antan
    -0.07
    æ¸ł
    -0.06
    encer
    -0.06
    POSITIVE LOGITS
    Ñģпа
    0.07
     nên
    0.07
    andi
    0.07
    изи
    0.07
    fasta
    0.07
    surf
    0.07
    ope
    0.07
    aray
    0.07
    鸳鸯
    0.06
    ä¸Ģ鸣
    0.06
    Activations Density 0.002%

    No Known Activations