© 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. 18367
    Prev
    Next
    INDEX
    Explanations

    rocket booster

    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
    宦
    -0.07
    succ
    -0.07
    afort
    -0.07
    onar
    -0.06
    ÑģÑĤÑĥпа
    -0.06
     Cron
    -0.06
     faj
    -0.06
     muj
    -0.06
     Cum
    -0.06
    =?
    -0.06
    POSITIVE LOGITS
    uhu
    0.09
    ä¸Ģå®ļç¨ĭ度
    0.08
    ://'
    0.08
    åłĤåłĤ
    0.07
     dual
    0.07
    åĬ©çIJĨ
    0.07
    绯éĹ»
    0.07
    åIJİèĩ³
    0.07
    raison
    0.06
     hong
    0.06
    Activations Density 0.040%

    No Known Activations