© 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. 12215
    Prev
    Next
    INDEX
    Explanations

    quasi-abstract, quantification, optimized, semi-retirement, experimental

    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
    æģ°
    -0.08
    opter
    -0.08
    oraf
    -0.08
    maal
    -0.08
    ORO
    -0.07
     essentially
    -0.07
     précisément
    -0.07
    æģ°æģ°
    -0.07
    ä¸įä»ħæľī
    -0.07
    ä¸įä»ħä»ħæĺ¯
    -0.07
    POSITIVE LOGITS
     Dan
    0.07
    ä½Ĩ以
    0.07
    hausen
    0.07
    ä½ĨåĽł
    0.07
    ught
    0.07
    ä¸ĭåIJĮ
    0.07
    Dan
    0.07
    ish
    0.07
    ä½Ĩèĩ³å°ij
    0.06
    -ish
    0.06
    Activations Density 0.665%

    No Known Activations