© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34990
    Prev
    Next
    INDEX
    Explanations

    reading input

    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
    Negative Logits
     bares
    -0.08
    imer
    -0.08
    kbd
    -0.08
    éĢļåĪĻ
    -0.07
     HOWEVER
    -0.07
    ause
    -0.07
    è¾īæĺł
    -0.07
    Msp
    -0.07
    ime
    -0.07
    jemu
    -0.07
    POSITIVE LOGITS
     if
    0.06
     enter
    0.06
    elsen
    0.06
     Polis
    0.06
    obby
    0.06
     assert
    0.06
    æ±ĤåĬ©
    0.06
    å¦Ĥæŀľä¸įèĥ½
    0.06
    åİŁèijĹ
    0.06
    èĭ¥ä¸į
    0.06
    Activations Density 0.048%

    No Known Activations