© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17417
    Prev
    Next
    INDEX
    Explanations

    invention, proposal, paper, article

    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
    esimo
    -0.09
    Writable
    -0.07
    erd
    -0.07
    ëĤĺ
    -0.07
    ordes
    -0.07
    иÑģÑĤеÑĢ
    -0.07
     estrang
    -0.07
     muster
    -0.07
    æı©
    -0.07
    æľĿå¤ķ
    -0.07
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.07
     coll
    0.07
    ureka
    0.07
    æļĤ
    0.07
    adge
    0.07
     lain
    0.07
     Vit
    0.07
    ä¸Ń使çĶ¨
    0.07
    æĶ¿
    0.06
    足
    0.06
    Activations Density 0.004%

    No Known Activations