© 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. 47327
    Prev
    Next
    INDEX
    Explanations

    numbers and divisibility questions

    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
     Messenger
    -0.08
    åĻª
    -0.07
    åŁºç¡Ģ
    -0.07
    ä¸Ģæī«
    -0.07
    perte
    -0.06
    ç¬Ķ趣éĺģ
    -0.06
     limitless
    -0.06
    寻
    -0.06
    å¼ķçĶ¨æĹ¥æľŁ
    -0.06
     stagnant
    -0.06
    POSITIVE LOGITS
    _configs
    0.07
    åħ¸
    0.07
    _conf
    0.07
    _configuration
    0.07
    IANA
    0.07
    yed
    0.07
    ÑĤва
    0.06
    inality
    0.06
    å¤ļæĸ¹
    0.06
    ÏİÏģα
    0.06
    Activations Density 0.012%

    No Known Activations