© 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. 19456
    Prev
    Next
    INDEX
    Explanations

    glm library paths

    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
    æľ¬æ³ķ
    -0.09
    æĬĬ头
    -0.07
    æĬĬåŃ©åŃIJ
    -0.07
    æĥ¯
    -0.07
    å·¡
    -0.07
    å¾Ģ常
    -0.06
    oir
    -0.06
     Rais
    -0.06
    ä¸ĢåIJij
    -0.06
    å·¡è§Ĩ
    -0.06
    POSITIVE LOGITS
    ssen
    0.08
    rosso
    0.08
    èo
    0.07
    EObject
    0.07
    çľĭåĪ°è¿Ļ
    0.07
    enville
    0.07
    Ñģен
    0.07
    avings
    0.07
    halten
    0.07
    Sheet
    0.07
    Activations Density 0.004%

    No Known Activations