© 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. 48976
    Prev
    Next
    INDEX
    Explanations

    divides or factor of

    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
    ich
    -0.08
    å¾Ĺ罪
    -0.07
    anh
    -0.07
    usser
    -0.06
    ä¸Ģ亮
    -0.06
    èĥ½èİ·å¾Ĺ
    -0.06
    ORN
    -0.06
     begun
    -0.06
    +
    -0.06
    à¸Ńิสระ
    -0.06
    POSITIVE LOGITS
    åĩłæ¬¡
    0.08
    isto
    0.08
    ortable
    0.07
    rá
    0.07
     پذ
    0.07
    _DEN
    0.07
    ái
    0.07
    ivi
    0.07
    intes
    0.07
     dign
    0.07
    Activations Density 0.004%

    No Known Activations