© 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. 56686
    Prev
    Next
    INDEX
    Explanations

    latex math expressions

    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
    utama
    -0.07
    åĬ¨è¾Ħ
    -0.06
     жела
    -0.06
    illo
    -0.06
    身边çļĦ人
    -0.06
     bruges
    -0.06
    åĩºå¤´
    -0.06
    ÙĪاÙĨات
    -0.06
    ary
    -0.06
    /=
    -0.06
    POSITIVE LOGITS
    åıĬ管çIJĨ
    0.08
    oyer
    0.08
    lds
    0.08
    haar
    0.08
    ammer
    0.08
    attel
    0.08
    arder
    0.07
    esch
    0.07
    çĶ©
    0.07
    gett
    0.07
    Activations Density 0.037%

    No Known Activations