© 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. 33825
    Prev
    Next
    INDEX
    Explanations

    example:

    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
    -login
    -0.09
    ,:
    -0.08
    {}".
    -0.08
    -scrollbar
    -0.08
    æĶ¿åįıåī¯ä¸»å¸Ń
    -0.08
     Nagy
    -0.07
    æľ¬åľ°å®Ŀ
    -0.07
    onie
    -0.07
     ander
    -0.07
    irim
    -0.07
    POSITIVE LOGITS
     ->
    0.08
    ->
    0.06
    æ¶Ĥ
    0.06
    继ç»Ń
    0.06
    ç»Ħ
    0.06
    éħį
    0.06
    ilhar
    0.06
    é
    0.05
    .cache
    0.05
    å·¥ä½ľéľĢè¦ģ
    0.05
    Activations Density 0.023%

    No Known Activations