© 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. 22712
    Prev
    Next
    INDEX
    Explanations

    entire

    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
    ä¹ĭä¸Ģæĺ¯
    -0.08
    ä¹ĭä¸Ģå°±æĺ¯
    -0.08
    æŀľçĦ¶
    -0.07
    uj
    -0.07
    ä¹ĭä¸Ģ
    -0.07
    actly
    -0.07
    ä¸Ģå®ļèĥ½
    -0.07
    ä¸Ģå®ļä¸įä¼ļ
    -0.07
    uns
    -0.07
    主è¦ģ为
    -0.07
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.17
    æĪĸéĥ¨åĪĨ
    0.16
     ÑĨеликом
    0.13
    æĪĸå¤ļ个
    0.11
    —including
    0.11
     except
    0.10
    à¹Ģลย
    0.10
     entire
    0.10
    å°±æĢķ
    0.10
    except
    0.09
    Activations Density 0.097%

    No Known Activations