© 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. 26071
    Prev
    Next
    INDEX
    Explanations

    steel, prospectively, monotonic, German, own

    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
    ä¸įä½Ĩ
    -0.07
     nejen
    -0.07
     Highest
    -0.07
    ENTO
    -0.07
    imum
    -0.07
    çİīå±±
    -0.07
    cznie
    -0.07
    ey
    -0.07
    пÑĮ
    -0.06
    urias
    -0.06
    POSITIVE LOGITS
    åį´å¾Ī
    0.09
    jav
    0.08
    åį´èĥ½
    0.08
     ÐĹаÑĤо
    0.08
    ä¸İä¹ĭ
    0.07
    åį´æĺ¯
    0.07
    åį´åľ¨
    0.07
    åIJİ宫
    0.07
    ë¡ľì§Ģ
    0.07
    Log
    0.07
    Activations Density 0.085%

    No Known Activations