© 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. 58785
    Prev
    Next
    INDEX
    Explanations

    code and dates

    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
    ouch
    -0.08
    ildo
    -0.07
    设å¤ĩçŃī
    -0.07
    arma
    -0.06
    enda
    -0.06
    lew
    -0.06
     ton
    -0.06
    endo
    -0.06
    MinMax
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    imonial
    0.08
    udel
    0.07
    êµī
    0.07
    áĢ±áĢ¬áĢĢáĢº
    0.07
    ucher
    0.07
    âĹĩâĹĨ
    0.07
    rica
    0.07
    OptionsResolver
    0.07
    adir
    0.07
    ä¸ĩåĽ½
    0.07
    Activations Density 0.632%

    No Known Activations