© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34714
    Prev
    Next
    INDEX
    Explanations

    weak reference

    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
    é²ľ
    -0.07
    баланÑģи
    -0.07
    LOPT
    -0.07
    åĴĮæĮijæĪĺ
    -0.07
    åĬĽéĩıåĴĮ
    -0.07
     Mondial
    -0.06
    yman
    -0.06
    junction
    -0.06
    prop
    -0.06
    centage
    -0.06
    POSITIVE LOGITS
    ëĤĺë§Ī
    0.08
    ward
    0.08
    æĢģ
    0.08
    ploy
    0.07
    imir
    0.07
     thụ
    0.07
    ldata
    0.07
    ãĤ¹ãĥļ
    0.07
    ãģ©
    0.07
    ä¸Ĭ马
    0.07
    Activations Density 0.001%

    No Known Activations