© 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. 12960
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols

    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
    oris
    -0.07
    缸éļı
    -0.06
    meld
    -0.06
    áĥ§
    -0.06
    UL
    -0.06
    beit
    -0.06
    åįķå±Ĥ
    -0.06
    Som
    -0.06
    noop
    -0.06
    çļĦé»ij
    -0.06
    POSITIVE LOGITS
    ì´Į
    0.08
    æį¢ä½į
    0.08
    itre
    0.08
    åĶ®è´§
    0.08
    upu
    0.08
    交åıī
    0.08
    enschaft
    0.08
    交æį¢
    0.08
    èIJ¤çģ«
    0.07
    üter
    0.07
    Activations Density 0.006%

    No Known Activations