© 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. 23287
    Prev
    Next
    INDEX
    Explanations

    absence or deficiency

    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
    ä¸įæĢķ
    -0.08
    ä¸įæĺ¯ä»Ģä¹Ī
    -0.07
    ä¸įä¼ļ被
    -0.07
    ä¸įè°Ī
    -0.07
    并ä¸į
    -0.07
     ern
    -0.07
    èĥĨåŃIJ
    -0.07
    èĻ½çĦ¶ä¸įæĺ¯
    -0.07
    没æľī
    -0.06
    å¿ĥæĥħ
    -0.06
    POSITIVE LOGITS
    ä¸īéĢļ
    0.07
    åıįä¹ĭ
    0.07
    elman
    0.07
    feit
    0.07
    conds
    0.07
    åIJį家
    0.07
     sebaliknya
    0.07
     вп
    0.06
    essa
    0.06
    æĮīçħ§åĽ½å®¶
    0.06
    Activations Density 0.197%

    No Known Activations