© 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. 33920
    Prev
    Next
    INDEX
    Explanations

    JSON structure"""

    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
    iran
    -0.08
    o
    -0.07
    å¸Ĥä¸Ń级人æ°ijæ³ķéĻ¢
    -0.07
    æ¬ł
    -0.07
    åĩ¡æľ¬ç½ij注æĺİ
    -0.07
    ä¸įè¿ľ
    -0.06
    ulton
    -0.06
    è¿ľæĸ¹
    -0.06
    lemn
    -0.06
    chaft
    -0.06
    POSITIVE LOGITS
    herits
    0.09
    uses
    0.08
    zelt
    0.08
    ired
    0.08
    ächen
    0.07
    æľīä¿¡å¿ĥ
    0.07
    å¹ħ度
    0.07
    ":[{"
    0.07
    OfString
    0.07
    lations
    0.07
    Activations Density 0.143%

    No Known Activations