© 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. 32854
    Prev
    Next
    INDEX
    Explanations

    problems and their solutions

    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
    æīĢéķ¿
    -0.07
    大鱼
    -0.07
    è²»
    -0.07
    onga
    -0.07
    schluss
    -0.07
    人åijĺ伤亡
    -0.07
    使çĶ¨è¯¥
    -0.07
    lich
    -0.06
    -authored
    -0.06
    å¨ģæѦ
    -0.06
    POSITIVE LOGITS
    管çIJĨçŃī
    0.13
     management
    0.11
    管çIJĨåıĬ
    0.10
    管çIJĨéĥ¨
    0.09
    åĪĨæŀIJä¸İ
    0.09
    åĪĨæŀIJåıĬ
    0.09
    管çIJĨä¸Ń
    0.09
    管çIJĨ
    0.09
    -aware
    0.09
    管çIJĨåĴĮ
    0.09
    Activations Density 0.540%

    No Known Activations