© 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. 22221
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    ieden
    -0.07
    _CONT
    -0.07
    idon
    -0.07
    _updates
    -0.06
    èį¡
    -0.06
    oleon
    -0.06
    æ¾İæ¹ĸ
    -0.06
     EventType
    -0.06
    çĩĥ
    -0.06
    çĶĺ
    -0.06
    POSITIVE LOGITS
     already
    0.09
     previously
    0.08
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.08
    _already
    0.08
    å·²æľī
    0.07
    already
    0.07
    å·²ç»ıæľī
    0.07
    å·²æľīçļĦ
    0.07
    olos
    0.07
    å·²ç»ıæĺ¯
    0.07
    Activations Density 0.087%

    No Known Activations