© 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. 2115
    Prev
    Next
    INDEX
    Explanations

    Big O notation

    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
    åłĤåłĤ
    -0.07
    滦
    -0.07
    kins
    -0.07
    rige
    -0.06
    brug
    -0.06
    roat
    -0.06
    elaar
    -0.06
    wurf
    -0.06
    رÙĬ
    -0.06
    æ»Ķ
    -0.06
    POSITIVE LOGITS
    ï¸İ
    0.09
     Kontaktd
    0.08
    çļĦä¸ľè¥¿
    0.07
    -ish
    0.07
    åĤ¾
    0.07
    ignées
    0.07
    ä¸ĢåĪĩ
    0.07
    everything
    0.07
    ktop
    0.07
    поÑĢа
    0.06
    Activations Density 0.001%

    No Known Activations