© 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. 34654
    Prev
    Next
    INDEX
    Explanations

    coefficient and constant

    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
    گاÙĩ
    -0.08
    amat
    -0.06
    emm
    -0.06
    گاÙĩÛĮ
    -0.06
    è¿Ļå°±æĺ¯æĪij
    -0.06
    ä¸Ģè¿ŀ
    -0.06
     Einh
    -0.06
    åħĪç¥ĸ
    -0.06
    ä¸ĢçĽĺ
    -0.06
    ort
    -0.06
    POSITIVE LOGITS
    perature
    0.09
    碰碰
    0.08
    resher
    0.08
    Innen
    0.08
    ì¹Ļ
    0.08
    ActionCode
    0.08
    <![
    0.08
    शà¥Ģ
    0.08
     ëĶ°
    0.08
    .createFrom
    0.07
    Activations Density 0.019%

    No Known Activations