© 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. 14178
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating actions or states

    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
    ä½Ĩèĩ³å°ij
    -0.08
    两ä¸ī
    -0.07
     Hud
    -0.07
    cheng
    -0.07
    -strokes
    -0.07
    icto
    -0.07
    à¸Ħำà¸Ļว
    -0.07
    æĪĸå¤ļ个
    -0.07
    æıIJé«ĺèѦæĥķ
    -0.07
    киÑı
    -0.07
    POSITIVE LOGITS
    ä¹ĭä¸Ģæĺ¯
    0.08
    åĺĽ
    0.08
    },{
    0.07
    çĻ½é¢Ĩ
    0.07
     besides
    0.07
    à¸Ĩ
    0.06
    å¤ļ为
    0.06
    ×ĵ×Ļ×Ŀ
    0.06
    ä¸Ń没æľī
    0.06
    ä¹ĭä¸Ģå°±æĺ¯
    0.06
    Activations Density 0.001%

    No Known Activations