© 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. 63871
    Prev
    Next
    INDEX
    Explanations

    selectively, of, content, condition, consumed

    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
    tig
    -0.10
    æīĵèµ·
    -0.08
    æ¯Ķå¦Ĥåľ¨
    -0.08
    OND
    -0.08
    ennt
    -0.08
    æĮĸæİĺåħ¬åı¸
    -0.07
    ukk
    -0.07
    ogle
    -0.07
    çİĭå°ı
    -0.07
    å¦Ĥä¸Ģ
    -0.07
    POSITIVE LOGITS
    ervi
    0.08
    ç³»ç»Łåľ°
    0.07
    åľ°åĿĢä½įäºİ
    0.07
    éĢļè¿ĩå¼Ģå±ķ
    0.07
     systematically
    0.06
    iming
    0.06
    zzo
    0.06
    ACHE
    0.06
    广ä¹ī
    0.06
    ache
    0.06
    Activations Density 0.195%

    No Known Activations