© 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. 19047
    Prev
    Next
    INDEX
    Explanations

    evaluating, study, realization, validity, guarantee

    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
    è¿Ļä¸ĢçĶŁ
    -0.07
    è¿Ļä¸ĸä¸Ĭ
    -0.06
    æ´Ľå¤«
    -0.06
    ä¸įè¦ģåIJĥ
    -0.06
    ä¸į欲
    -0.06
    বি
    -0.06
     please
    -0.06
    ibility
    -0.06
    icar
    -0.06
    ä»Ģä¹ĪæĦıæĢĿ
    -0.06
    POSITIVE LOGITS
    è¶
    0.08
    ÑĶ
    0.07
     probing
    0.07
    åºĩ
    0.07
     cmds
    0.07
    bsp
    0.07
    noinspection
    0.07
    çīĽè§Ĵ
    0.07
    å°ıéĩij
    0.07
    roj
    0.07
    Activations Density 0.003%

    No Known Activations