© 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. 28362
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    -turned
    -0.09
    ime
    -0.07
    çºĤ
    -0.07
    uca
    -0.07
    èĪ¬çļĦ
    -0.07
    æĦŁçļĦ
    -0.07
     Gunn
    -0.07
    æĢ§åıĬ
    -0.07
    kena
    -0.07
    ç´
    -0.07
    POSITIVE LOGITS
    eters
    0.10
    ersen
    0.06
    ahren
    0.06
    å·¦åı³
    0.06
    chien
    0.06
    第ä¸ĢåŃ¦æľŁ
    0.06
    éĩijåŃIJ
    0.06
    ¹
    0.06
    asses
    0.06
    rages
    0.06
    Activations Density 0.107%

    No Known Activations