© 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. 29449
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

    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
    çĬ¯
    -0.07
     disg
    -0.07
    å¼łæī¬
    -0.07
    endoza
    -0.07
    onus
    -0.06
    ä¸ŃæŬ
    -0.06
    çĬ¯çļĦ
    -0.06
    agma
    -0.06
    èĢĮçĶŁ
    -0.06
    abri
    -0.06
    POSITIVE LOGITS
     appunto
    0.10
    วà¸Ī
    0.08
    æĪij们éĥ½æĺ¯
    0.08
    ĥĿ
    0.08
    stelling
    0.08
     ÑģобÑģÑĤвенно
    0.08
    ä½łä¸įçŁ¥éģĵ
    0.08
    stwo
    0.08
    åĽ½ä¹ĭ
    0.07
    ä½łæĺ¯æĪijçļĦ
    0.07
    Activations Density 0.210%

    No Known Activations