© 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. 19364
    Prev
    Next
    INDEX
    Explanations

    deoxyribose

    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
    èĢ³çĽ®
    -0.08
    ETO
    -0.07
    é¬ĵ
    -0.07
    æĬĬå·¥ä½ľ
    -0.07
    ÑĤки
    -0.07
    ÑĤÑİ
    -0.07
    etto
    -0.07
    chers
    -0.07
    åħĨ
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    POSITIVE LOGITS
    èĦĨ
    0.07
    æľ¨æľī
    0.07
    gone
    0.07
    коно
    0.07
    ois
    0.07
     Dane
    0.07
    JoinColumn
    0.07
     vulnerable
    0.06
    crete
    0.06
    æµĨ
    0.06
    Activations Density 0.012%

    No Known Activations