© 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. 22238
    Prev
    Next
    INDEX
    Explanations

    unconfirmed or uncertain events

    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
    del
    -0.06
    åīįéĿ¢
    -0.06
    rh
    -0.06
    çļĦæ¦Ĥçİĩ
    -0.06
     ky
    -0.05
    åŁĶ
    -0.05
    оÑĢо
    -0.05
    骨干
    -0.05
    æľ¬èº«å°±
    -0.05
    ãģijãĤĵ
    -0.05
    POSITIVE LOGITS
    ëĤĺë§Ī
    0.10
     ÑıкобÑĭ
    0.09
    olini
    0.09
    ë§IJë¡ľ
    0.09
    ¬¸
    0.08
    regon
    0.08
     keresztül
    0.08
     бÑĥдÑĤо
    0.08
    -controls
    0.08
    ëĿ¼ëıĦ
    0.08
    Activations Density 0.347%

    No Known Activations