© 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. 60775
    Prev
    Next
    INDEX
    Explanations

    config and options

    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
    awah
    -0.08
    çļĦ好æĪIJ绩
    -0.08
    åĩºæ²¡
    -0.07
    akor
    -0.07
     notif
    -0.07
    è¦ģä¸į
    -0.07
    Locker
    -0.07
    è¯ĨåĪ«åı·
    -0.07
    ukkan
    -0.07
    abaj
    -0.07
    POSITIVE LOGITS
     parameters
    0.10
    parameters
    0.09
     Parameters
    0.09
    åıĤæķ°
    0.09
     settings
    0.09
     knobs
    0.08
    urator
    0.08
     паÑĢамеÑĤÑĢÑĭ
    0.08
    Parameters
    0.08
    _parameters
    0.08
    Activations Density 0.267%

    No Known Activations