© 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. 26345
    Prev
    Next
    INDEX
    Explanations

    diff line prefixes

    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
    mira
    -0.08
    åĩºæĿ¥çļĦ
    -0.08
    .pivot
    -0.07
    第ä¸Ģ个
    -0.07
    çļĦ第ä¸Ģ个
    -0.07
    enius
    -0.07
    cis
    -0.07
    unik
    -0.07
    ServiceProvider
    -0.07
    fication
    -0.07
    POSITIVE LOGITS
    obr
    0.07
    çĶ©
    0.07
    į
    0.07
    èĬ³èįī
    0.07
    IDS
    0.07
    羣
    0.06
    lash
    0.06
    æ®ĥ
    0.06
    trace
    0.06
    æĬĹ
    0.06
    Activations Density 0.003%

    No Known Activations