© 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. 27091
    Prev
    Next
    INDEX
    Explanations

    .begin() iterators

    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
    å¤ľæ·±
    -0.07
    继ç»Ńåľ¨
    -0.07
     ngại
    -0.07
    èģĶ绾
    -0.07
    ä¸Ģæīĭ
    -0.07
    çŃĭ
    -0.06
    inh
    -0.06
    ulum
    -0.06
    计çļĦ
    -0.06
    ön
    -0.06
    POSITIVE LOGITS
    æ¸Ĺåĩº
    0.08
    akest
    0.07
    aszt
    0.07
    estand
    0.07
    amarca
    0.07
    ANDOM
    0.07
    ipes
    0.07
    ERE
    0.06
     respek
    0.06
    اÙĨØ´
    0.06
    Activations Density 0.004%

    No Known Activations