© 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. 29629
    Prev
    Next
    INDEX
    Explanations

    mathematical vector dimensions

    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
    stad
    -0.08
    igna
    -0.07
    åIJ®
    -0.07
    åĵĪæĭī
    -0.07
    å¿
    -0.07
     wÅĤaÅĽnie
    -0.07
    èijĹ
    -0.07
     betreff
    -0.07
     ÑĢаÑģка
    -0.07
    liner
    -0.07
    POSITIVE LOGITS
    arts
    0.07
    Ñįг
    0.07
    èĮħ
    0.06
    åŃ¦ä¹łçĶŁæ´»
    0.06
    ãĥ¬ãĤ¹ãĥĪ
    0.06
    ago
    0.06
    redis
    0.06
    rus
    0.06
    ĶĦ
    0.06
    nc
    0.06
    Activations Density 0.016%

    No Known Activations