© 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. 47654
    Prev
    Next
    INDEX
    Explanations

    asking "how to" questions

    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
    atform
    -0.08
    æľ¬é¢ĺåĪĨæŀIJ
    -0.07
    彬
    -0.07
    äºĨä¸Ģå±Ĥ
    -0.07
    scri
    -0.07
    常人
    -0.07
    aison
    -0.07
    å¨ģæĸ¯
    -0.07
    解åĨ³éĹ®é¢ĺçļĦ
    -0.07
    оÑĢод
    -0.07
    POSITIVE LOGITS
     safely
    0.08
     reliably
    0.08
    æĹ¢èĥ½
    0.07
    ç¢ºå®Łãģ«
    0.07
    ä¸ĢåIJį
    0.07
     successfully
    0.07
    etch
    0.07
    好åij¢
    0.07
     reliable
    0.07
    æľĢä½³çļĦ
    0.07
    Activations Density 0.050%

    No Known Activations