© 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. 21277
    Prev
    Next
    INDEX
    Explanations

    Constructor Cause constructor MessageCause

    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
    -0.07
     Hold
    -0.07
    èĥĸèĥĸ
    -0.07
    ç¢
    -0.07
    ilde
    -0.07
    大æľī
    -0.07
    åłĤ
    -0.06
    æľĶ
    -0.06
     flor
    -0.06
    åłĤçļĦ
    -0.06
    POSITIVE LOGITS
    ISTRA
    0.08
    йÑģ
    0.07
    ipot
    0.07
     watched
    0.07
    _DECLS
    0.07
    elter
    0.06
    æĪij们ä¼ļ尽快
    0.06
    łĢ
    0.06
    agara
    0.06
    rades
    0.06
    Activations Density 0.084%

    No Known Activations