© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63820
    Prev
    Next
    INDEX
    Explanations

    undes, ob, obs

    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
    GLOBALS
    -0.09
    macher
    -0.08
    ãĤĤãģ¡
    -0.08
    åłª
    -0.08
    å·®ä¸įå¤ļäºĨ
    -0.08
    åijĺ
    -0.08
    ayani
    -0.08
    esture
    -0.08
    icarbon
    -0.08
    éĢĤåIJĪäºİ
    -0.07
    POSITIVE LOGITS
    ly
    0.08
    -hidden
    0.07
    ä¹ĭçī©
    0.07
    å¾Ĺå¾Ī
    0.07
    LY
    0.06
    ¼
    0.06
    ä¹ĭè¾Ī
    0.06
    sey
    0.06
    åĥ»
    0.06
     módon
    0.06
    Activations Density 0.001%

    No Known Activations