© 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. 40768
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    è¿ŀ带责任
    -0.07
    zew
    -0.07
    éªĭ
    -0.07
    ĮĢ
    -0.06
    gaard
    -0.06
    å¾Ħ
    -0.06
    ä¸įéĶĻ
    -0.06
    æĥĬå¿ĥ
    -0.06
    adero
    -0.06
    åĸ½
    -0.06
    POSITIVE LOGITS
    ç¹°
    0.09
    ingin
    0.08
    ocup
    0.08
    óa
    0.07
     electrons
    0.07
    ä¸ī室
    0.07
    aki
    0.07
    OMO
    0.07
    çĶµåŃIJä¿¡æģ¯
    0.07
    IRA
    0.07
    Activations Density 0.007%

    No Known Activations