© 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. 8486
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings and identifiers

    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
    éĺ¶
    -0.07
    combe
    -0.06
    .tb
    -0.06
     variable
    -0.06
    /cop
    -0.06
     uniform
    -0.06
     +=
    -0.06
    éļİ
    -0.06
    opot
    -0.06
     Balk
    -0.06
    POSITIVE LOGITS
    intang
    0.08
    åı¬
    0.07
    iled
    0.07
    å°¾éħĴ
    0.07
    æĩ
    0.07
    ุà¸Ķ
    0.07
    -trash
    0.07
    eming
    0.07
    ucha
    0.07
    ocha
    0.07
    Activations Density 0.051%

    No Known Activations