© 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. 32886
    Prev
    Next
    INDEX
    Explanations

    longer, decreased, fewer

    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
     немед
    -0.07
     enough
    -0.07
     even
    -0.07
    è¿ŀåŁİ
    -0.07
    ç»Ŀ大å¤ļæķ°
    -0.07
    çľĭå¾Ĺè§ģ
    -0.07
    åıªæľīéĢļè¿ĩ
    -0.07
    åı²
    -0.07
    è¶³å¤Ł
    -0.07
    å®Į好
    -0.07
    POSITIVE LOGITS
    åĢ¾åIJijäºİ
    0.10
     tends
    0.10
     somewhat
    0.09
    æŁIJäºĽ
    0.09
     cenderung
    0.08
     poorer
    0.08
     certain
    0.08
    åĤ¾åIJij
    0.08
     fewer
    0.08
    åľ¨æŁIJäºĽ
    0.08
    Activations Density 0.089%

    No Known Activations