© 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. 28306
    Prev
    Next
    INDEX
    Explanations

    connecting things or ideas

    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
     unber
    -0.08
    æĪijæĿ¥è¯´
    -0.08
    为代表
    -0.08
    byn
    -0.08
    ä»Ģä¹Īéĥ½ä¸į
    -0.08
    ANNER
    -0.07
    oze
    -0.07
    verfahren
    -0.07
    ëĮĢíijľ
    -0.07
    umber
    -0.07
    POSITIVE LOGITS
     broader
    0.08
     relevance
    0.08
     táºŃn
    0.07
    ç´§æī£
    0.07
    çİ°å®ŀæĦıä¹ī
    0.07
    èIJ½èĦļçĤ¹
    0.07
     context
    0.07
     concepts
    0.07
     relate
    0.07
    context
    0.06
    Activations Density 0.034%

    No Known Activations