© 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. 63308
    Prev
    Next
    INDEX
    Explanations

    explaining something complex

    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
    øv
    -0.08
    geschlossen
    -0.08
    åİŁå§ĭçļĦ
    -0.08
    æľĢæĸ°æ¶Īæģ¯
    -0.08
    quel
    -0.07
    uyo
    -0.07
    ickl
    -0.07
    hled
    -0.07
    urna
    -0.07
    æľīç¦ı
    -0.07
    POSITIVE LOGITS
     misunderstood
    0.08
     obscure
    0.07
     explained
    0.07
    еÑī
    0.07
     assez
    0.07
     misrepresented
    0.07
     explicado
    0.06
     relatively
    0.06
    åĨ·éŨ
    0.06
     Dund
    0.06
    Activations Density 0.088%

    No Known Activations