© 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. 25692
    Prev
    Next
    INDEX
    Explanations

    pump therapy, fractional resurfacing, RW lock, EF out

    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
    å½ĵå¿ĥ
    -0.08
    utton
    -0.07
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.07
    åįĬå±±
    -0.07
    ³
    -0.07
    à¸ķัà¸Ļ
    -0.07
    fahr
    -0.07
    otor
    -0.06
    以åıĬå¦Ĥä½ķ
    -0.06
    åIJŀåIJIJ
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.08
    ·
    0.08
    shaw
    0.07
    æ³
    0.07
    cente
    0.07
    shot
    0.07
    rray
    0.07
    èĢģåİ»
    0.07
    ÅŁi
    0.07
     gerek
    0.06
    Activations Density 0.037%

    No Known Activations