© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48436
    Prev
    Next
    INDEX
    Explanations

    inverse or fractional powers

    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
    овой
    -0.08
     sekali
    -0.08
    åѦçłĶ究
    -0.07
    ziger
    -0.07
    ../../
    -0.07
    arana
    -0.07
     ÑģобÑĸ
    -0.07
    'e
    -0.07
    igration
    -0.07
    ewise
    -0.07
    POSITIVE LOGITS
    0.09
    Ù°
    0.09
    äj
    0.07
     говоÑĢÑı
    0.07
    innen
    0.07
    ாள
    0.06
    è¨ĢãģĪãģ°
    0.06
    èĶĹ
    0.06
    amarin
    0.06
    ités
    0.06
    Activations Density 0.004%

    No Known Activations