© 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. 41761
    Prev
    Next
    INDEX
    Explanations

    lllllllllllllllllllll

    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
    idente
    -0.06
    itora
    -0.06
    æݧ
    -0.06
    иÑģÑĤ
    -0.06
    ervers
    -0.06
    ilst
    -0.06
     rst
    -0.06
    essant
    -0.06
    dispatch
    -0.06
    atanya
    -0.06
    POSITIVE LOGITS
    ëĭ¤ê°Ģ
    0.07
    æĸĩçIJĨ
    0.07
    pah
    0.07
    åįģåħ«ç«ł
    0.07
     prega
    0.07
    对æīĢ
    0.06
    ä¸Ĭå¹´åIJĮæľŁ
    0.06
    abal
    0.06
    almaz
    0.06
    ként
    0.06
    Activations Density 0.009%

    No Known Activations