© 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. 62585
    Prev
    Next
    INDEX
    Explanations

    question words

    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
    endid
    -0.07
    itemap
    -0.07
    annage
    -0.07
    Äįk
    -0.07
    oot
    -0.07
    umni
    -0.07
     majd
    -0.07
    æł¹æľ¬å°±æ²¡æľī
    -0.06
    æŀĹä¸ļå±Ģ
    -0.06
    achr
    -0.06
    POSITIVE LOGITS
    对æѤ
    0.14
     however
    0.12
    è¿Ļæĸ¹éĿ¢çļĦ
    0.12
    为æѤ
    0.12
     hierv
    0.11
    åľ¨è¿Ļæĸ¹éĿ¢
    0.11
    ä¸İæѤ
    0.11
    å°įæѤ
    0.11
    however
    0.11
    ãģĿãĤĵãģª
    0.11
    Activations Density 1.268%

    No Known Activations