© 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. 42680
    Prev
    Next
    INDEX
    Explanations

    momentum cut

    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
    onet
    -0.09
    大åĬĽå®ŀæĸ½
    -0.07
    оÑĢе
    -0.07
    ensi
    -0.07
    å¼Ĥå½¢
    -0.07
    ä¸įå¾Ĺ转载
    -0.07
    åIJİå¤ĩ
    -0.07
    å¼ĢèĬ±
    -0.07
    UBL
    -0.07
    éĹ°
    -0.07
    POSITIVE LOGITS
    çŁ¢
    0.09
    æľĭåħĭ
    0.07
    reu
    0.07
     Chauss
    0.07
    eld
    0.07
     photons
    0.06
    åĴĮè§ĦèĮĥ
    0.06
     blat
    0.06
    æĿŁ
    0.06
    äck
    0.06
    Activations Density 0.002%

    No Known Activations