© 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. 58826
    Prev
    Next
    INDEX
    Explanations

    git diff file paths

    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
    alach
    -0.08
    以ä¸ĬåĨħ容
    -0.07
    awa
    -0.07
    çķľ
    -0.07
     Rowling
    -0.06
    uze
    -0.06
    esco
    -0.06
    omotive
    -0.06
    å¿ħæľī
    -0.06
    ãģ¾ãģĹãģ¦
    -0.06
    POSITIVE LOGITS
    Õ¼
    0.09
    )':
    0.07
    logo
    0.07
    ÄĽn
    0.07
    ünftig
    0.07
    ä¸Ģæĸ°
    0.07
    ัà¸ĩà¸ģ
    0.07
    ëĭ«
    0.07
     nowhere
    0.06
    ç¬Ļ
    0.06
    Activations Density 0.018%

    No Known Activations