© 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. 58293
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or roots

    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±¹
    -0.07
    ç¯Ŀ
    -0.07
    峪
    -0.07
    íķ©
    -0.07
     Kurd
    -0.07
    ç§ī
    -0.07
    Ø´ÙĬØ©
    -0.07
    inherits
    -0.07
     cobrar
    -0.07
    éħİ
    -0.07
    POSITIVE LOGITS
    stech
    0.08
    unities
    0.07
    uin
    0.07
    ovit
    0.07
    oyo
    0.06
    çªģçł´åı£
    0.06
    åħĪçĶ¨
    0.06
    ihn
    0.06
    weep
    0.06
    æĸĩç§ĺ
    0.06
    Activations Density 0.003%

    No Known Activations