© 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. 58288
    Prev
    Next
    INDEX
    Explanations

    at locations or possessions

    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
    sze
    -0.08
    èѦåĬĽ
    -0.08
    ä¸ĢæıIJ
    -0.07
     sá»ī
    -0.07
    æĪ¿å®¢
    -0.07
    ä¸įè¦ģå¿ĺäºĨ
    -0.07
    ssä
    -0.07
    丰åı°åĮº
    -0.07
    åħ¨è·¯æ®µ
    -0.07
    luit
    -0.07
    POSITIVE LOGITS
     confines
    0.08
    æ´Ĵ
    0.07
    åįĥ人
    0.07
    æŃ£è§ĦåĮ»éĻ¢
    0.07
     designated
    0.07
     dil
    0.07
    å¯ĵ
    0.06
    ä¸ĵçĶ¨
    0.06
    è®¾åľ¨
    0.06
     premises
    0.06
    Activations Density 0.942%

    No Known Activations