© 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. 15118
    Prev
    Next
    INDEX
    Explanations

    numbers like 2, 0, 1, 3

    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
    以åıĬ对
    -0.07
     sowie
    -0.07
    以åıĬåľ¨
    -0.07
    âĢ¦âĢ¦
    -0.07
    以åıĬå¦Ĥä½ķ
    -0.07
    æĢ§ä»¥åıĬ
    -0.06
    ÙĤÛĮ
    -0.06
    以åıĬ
    -0.06
    /vector
    -0.06
    以åıĬä¸İ
    -0.06
    POSITIVE LOGITS
    printer
    0.08
    _mime
    0.08
    .sat
    0.07
    иÑĤаÑĤÑĮ
    0.07
    aben
    0.07
    ebles
    0.07
    ä¸Ĭä¸ĢæĿ¡
    0.07
    avais
    0.07
     Sat
    0.07
    emens
    0.07
    Activations Density 0.010%

    No Known Activations