© 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. 47528
    Prev
    Next
    INDEX
    Explanations

    allele pairs

    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
    зой
    -0.07
    åħ¹
    -0.07
    бак
    -0.07
    yse
    -0.07
    بÙĪ
    -0.07
    çī©çļĦ
    -0.07
    诸å¦Ĥ
    -0.07
    OPS
    -0.07
    ëĤ©
    -0.07
    OFF
    -0.07
    POSITIVE LOGITS
    /pp
    0.07
    å½¢å¼ıçļĦ
    0.07
    ì§ľ
    0.06
    /ay
    0.06
    /null
    0.06
    ta
    0.06
     ta
    0.06
    สล
    0.06
    åħ±åĴĮåĽ½
    0.06
    çĽ¸ä¼ł
    0.06
    Activations Density 0.001%

    No Known Activations