© 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. 43193
    Prev
    Next
    INDEX
    Explanations

    item ( pid , 1 )

    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
    ç§ī
    -0.08
    æ¡Ķ
    -0.08
     пова
    -0.07
    æĸ¯åį¡
    -0.07
     глазами
    -0.07
    iche
    -0.07
    Forge
    -0.07
    pson
    -0.07
    èı²å°Ķå¾·
    -0.07
    大å¦Ī
    -0.07
    POSITIVE LOGITS
    exact
    0.08
     exact
    0.08
    èĥİ
    0.08
     Exact
    0.07
    æĥĬ
    0.07
    精确
    0.07
    群
    0.07
    缩å°ı
    0.07
    Exact
    0.07
    æĹ¢çĦ¶
    0.07
    Activations Density 0.075%

    No Known Activations