© 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. 17585
    Prev
    Next
    INDEX
    Explanations

    ideology of

    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
    umping
    -0.07
    ড়া
    -0.07
    ç´łæľī
    -0.07
    estina
    -0.07
    pst
    -0.07
    æ¾İ
    -0.07
    éģ¨
    -0.07
    idel
    -0.07
    sour
    -0.07
    owitz
    -0.07
    POSITIVE LOGITS
    äºij
    0.08
     voire
    0.07
    zos
    0.07
    åĩºäºº
    0.07
    çĶļèĩ³
    0.06
    å·¥äºĭ
    0.06
     fond
    0.06
    ä¸į容
    0.06
    çĶļèĩ³æĺ¯
    0.06
    ØŃاء
    0.06
    Activations Density 0.002%

    No Known Activations