© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16942
    Prev
    Next
    INDEX
    Explanations

    kindly repeat, in each case, possible, varied, opinion, known

    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
    νοÏį
    -0.08
    arga
    -0.08
    ÙĪÙħÙĬØ©
    -0.07
    vertret
    -0.07
    umn
    -0.07
    nu
    -0.07
    çīĩä¸Ń
    -0.07
    à¸ĺร
    -0.07
    ambo
    -0.07
    emas
    -0.07
    POSITIVE LOGITS
    uire
    0.06
     asci
    0.06
    çĴŀ
    0.06
     Comp
    0.06
    0.06
    zip
    0.06
    ISTR
    0.06
    çĭ¸
    0.06
     saj
    0.06
    ylum
    0.06
    Activations Density 0.004%

    No Known Activations