© 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. 24515
    Prev
    Next
    INDEX
    Explanations

    under this

    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
     er
    -0.07
     Bos
    -0.06
     factors
    -0.06
    çIJĨ解为
    -0.06
    æĸ¹éĿ¢
    -0.06
    鼷
    -0.06
    åĨĪ
    -0.06
    çĻ¾è®¡
    -0.06
    æĺ¯å¾Ī
    -0.06
    缮
    -0.06
    POSITIVE LOGITS
    éļħ
    0.09
     nutshell
    0.08
    #,
    0.08
    æ¯ıä¸Ģ次
    0.08
    ä»»ä½ķä¸Ģç§į
    0.07
    Å¡nÃŃ
    0.07
    typ
    0.07
    /classes
    0.07
    yer
    0.07
    weeney
    0.07
    Activations Density 0.310%

    No Known Activations