© 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. 29031
    Prev
    Next
    INDEX
    Explanations

    large scale applications

    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
    ستاÙĨ
    -0.08
    éĩįéĩįçļĦ
    -0.07
     utmost
    -0.07
    à¹ģà¸ģà¹Ī
    -0.07
    ween
    -0.07
    ounge
    -0.07
    åIJĬéĶĢ
    -0.07
    Playable
    -0.07
    æĤ£å¤Ħ
    -0.07
    满满
    -0.07
    POSITIVE LOGITS
    ç¨ĭ度ä¸Ĭ
    0.10
    大è§Ħ模çļĦ
    0.10
    è§Ħ模
    0.10
    大è§Ħ模
    0.09
    è§Ħ模çļĦ
    0.09
    -scale
    0.09
    çŃī大åŀĭ
    0.08
    次çļĦ
    0.08
    êµī
    0.08
    ãģĭãģ¤
    0.08
    Activations Density 0.059%

    No Known Activations