© 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. 46007
    Prev
    Next
    INDEX
    Explanations

    apparently, that

    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
    udos
    -0.08
    æī«çłģåħ³æ³¨
    -0.08
    ignon
    -0.08
    æģIJ
    -0.08
    å¦Ĥæŀľæĺ¯
    -0.08
    çļĦæĺ¯ä»Ģä¹Ī
    -0.07
    iox
    -0.07
    inary
    -0.07
    åħ¶å®ŀ
    -0.07
    ippi
    -0.07
    POSITIVE LOGITS
    ä½łè¿Ļä¹Ī
    0.08
    è¿Ļä¹Ī说
    0.07
     demikian
    0.07
    æľīæѤ
    0.07
     already
    0.07
     forth
    0.07
    è¿Ļä¹Ī
    0.07
    è¿ĻèĪ¬
    0.07
    ê»ı
    0.07
    ÙĦاء
    0.07
    Activations Density 0.008%

    No Known Activations