© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 846
    Prev
    Next
    INDEX
    Explanations

    void function declarations

    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
    .Pending
    -0.07
    份
    -0.06
    _IOCTL
    -0.06
    ä¸įå¹²
    -0.06
    æĭĶåĩº
    -0.06
    .safe
    -0.06
    Flo
    -0.06
    ehr
    -0.06
    ooth
    -0.06
    uppe
    -0.06
    POSITIVE LOGITS
    usiness
    0.07
    ä¸įæ³ķ
    0.07
    inem
    0.07
    gary
    0.07
    éĻįè´¹
    0.07
    áĥĺáĥľ
    0.07
    unami
    0.07
    оÑĩÑĮ
    0.07
    nung
    0.07
    .setOutput
    0.07
    Activations Density 0.247%

    No Known Activations