© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49275
    Prev
    Next
    INDEX
    Explanations

    turn issues into opportunities

    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
    å§ĭèĩ³
    -0.08
    æľ¬æĢ§
    -0.08
    ä½ľä¸º
    -0.08
    áĢĦáĢºáĢ¸
    -0.07
    recent
    -0.07
    STATUS
    -0.07
    ä¸Ģ个好çļĦ
    -0.07
    umente
    -0.07
    身为
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    POSITIVE LOGITS
    åħ³æ³¨çļĦçĦ¦çĤ¹
    0.09
    åIJįåī¯åħ¶å®ŀçļĦ
    0.09
     actionable
    0.09
    çļĦä¸Ģéĥ¨åĪĨ
    0.08
    æľīæį®
    0.08
     usable
    0.08
     manageable
    0.08
     íķĺëĤĺìĿĺ
    0.08
     something
    0.08
    æľīçĶŁ
    0.07
    Activations Density 0.154%

    No Known Activations