© 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. 46281
    Prev
    Next
    INDEX
    Explanations

    IDs and foreign keys

    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
    оÑĤÑĢе
    -0.08
    mann
    -0.07
    lee
    -0.07
    luft
    -0.07
    راÙĤ
    -0.07
    æ¶İ
    -0.07
    壬
    -0.07
    æīĭ段
    -0.07
     सà¥ģ
    -0.07
    oire
    -0.07
    POSITIVE LOGITS
    çĭ©
    0.07
     parent
    0.07
    -parent
    0.07
     å¼ķçĶ¨
    0.07
    ç´IJ
    0.07
    çIJĨ
    0.07
    âĢ¦ãĢį
    0.07
    parent
    0.07
     péd
    0.07
    aktu
    0.06
    Activations Density 0.183%

    No Known Activations