© 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. 32787
    Prev
    Next
    INDEX
    Explanations

    for loop iteration

    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
    ence
    -0.07
    æĿ¥èĩª
    -0.06
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    -0.06
    ifth
    -0.06
    ↵
    -0.06
    :
    -0.06
    ift
    -0.06
    éĿŀ常好
    -0.05
    ID
    -0.05
     rad
    -0.05
    POSITIVE LOGITS
    大åĪ°
    0.12
    åį³æĹ¥èµ·
    0.10
    微信åħ¬ä¼Ĺå¹³åı°
    0.09
     outset
    0.09
    å§ĭèĩ³ç»Ī
    0.09
    sut
    0.09
    ocoder
    0.08
    esos
    0.08
    _INITIALIZER
    0.08
    itie
    0.08
    Activations Density 0.018%

    No Known Activations