© 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. 21124
    Prev
    Next
    INDEX
    Explanations

    positive sentiment modifiers

    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
    amah
    -0.09
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.09
    shaw
    -0.08
    akkan
    -0.08
    好åij¢
    -0.08
    ignan
    -0.08
    好åķĬ
    -0.08
    ãģĵãģĿ
    -0.08
    ahari
    -0.07
    hton
    -0.07
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.08
    èĸ«
    0.07
    ä½Ĩä¹Ł
    0.07
    ä¹ŁæĽ´
    0.06
    ä½Ĩä¹Łæľī
    0.06
     but
    0.06
    .
    0.06
    ik
    0.06
     geweest
    0.06
    æѤæŶçļĦ
    0.06
    Activations Density 0.073%

    No Known Activations