© 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. 56038
    Prev
    Next
    INDEX
    Explanations

    license file. package bn256 // For details of the algorithms used, see "Multiplication and Squaring on // Pairing-Friendly Fields"

    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
    ekt
    -0.07
    人æīĭ
    -0.07
    ç±
    -0.07
    akat
    -0.07
    管
    -0.07
    ç¯ĵ
    -0.07
    orten
    -0.06
    intl
    -0.06
     sen
    -0.06
    æĥ¦
    -0.06
    POSITIVE LOGITS
    InBackground
    0.08
    个人è§ĤçĤ¹
    0.07
    ķĮ
    0.07
    åİŁæĸĩåĩºå¤Ħ
    0.07
    onio
    0.07
    igators
    0.07
     îns
    0.07
    ücke
    0.07
    ÙĤاÛĮ
    0.07
    ä¿Ŀè¯ģåħ¶
    0.07
    Activations Density 0.119%

    No Known Activations