© 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. 15670
    Prev
    Next
    INDEX
    Explanations

    read only or const

    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
    æĪIJé¾Ļ
    -0.07
     rasse
    -0.07
    åĽŀæĹĭ
    -0.07
    ner
    -0.07
    æ·¹
    -0.07
     Numéro
    -0.07
    æ¡¥æŀ¶
    -0.07
    æ¢Ń
    -0.07
    bildungs
    -0.07
    arcy
    -0.07
    POSITIVE LOGITS
     restriction
    0.09
    ahr
    0.09
    -only
    0.08
    ensive
    0.08
     immutable
    0.08
     access
    0.08
    _READONLY
    0.08
    æħĭ
    0.07
     readOnly
    0.07
    ovable
    0.07
    Activations Density 0.087%

    No Known Activations