© 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. 30553
    Prev
    Next
    INDEX
    Explanations

    together, combine, unite

    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
    åħ¶è¡Į为
    -0.08
    åĽłä¸ºåħ¶
    -0.07
    举åĬ¨
    -0.07
    Ãłnh
    -0.07
    hai
    -0.07
     behalf
    -0.07
    ä¸įå¾Ĺå·²
    -0.07
    оваÑĤелÑĮ
    -0.07
    ãģĭãģ£ãģŁãģ§ãģĻ
    -0.07
     Finan
    -0.07
    POSITIVE LOGITS
     nhau
    0.11
    èĢĮæĪIJçļĦ
    0.10
    èĢĮæĪIJ
    0.08
    æīįæľīäºĨ
    0.08
     elkaar
    0.07
    å½¢æĪIJä¸Ģ个
    0.07
    äºİä¸Ģ身
    0.07
    åľ¨ä¸Ģèµ·
    0.07
    çĿĢçĶ¨
    0.07
    äºİä¸Ģä½ĵ
    0.07
    Activations Density 0.022%

    No Known Activations