© 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. 34467
    Prev
    Next
    INDEX
    Explanations

    HTTP server that receives POST

    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
     "..
    -0.09
     "**
    -0.08
     "...
    -0.08
     **"
    -0.08
     Paypal
    -0.07
     *"
    -0.07
     counterparts
    -0.07
    ä¸įçŁ¥éģĵä½ł
    -0.07
    åIJİåı°åĽŀå¤į
    -0.07
    汽车ç½ij
    -0.07
    POSITIVE LOGITS
    âĢij
    0.13
    âĢ
    0.12
    ’T
    0.08
     ÂŃ
    0.07
    ullo
    0.07
     specialised
    0.07
     plainly
    0.07
    ÑĮÑİ
    0.07
    ÂŃ
    0.07
    Âł
    0.07
    Activations Density 0.002%

    No Known Activations