© 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. 55217
    Prev
    Next
    INDEX
    Explanations

    inexpensive, simple, easy, cheap, convenient

    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
     narrower
    -0.10
    æĽ´æ·±
    -0.09
    _blocking
    -0.09
    ÎŃν
    -0.09
    å¾ĹæĽ´
    -0.09
    为äºĨæĽ´å¥½çļĦ
    -0.08
     stricter
    -0.08
     prém
    -0.08
    бÑĢе
    -0.08
     smoother
    -0.08
    POSITIVE LOGITS
    å»ī
    0.13
     inexpensive
    0.13
     simple
    0.11
    ç®Ģ便
    0.11
     easy
    0.11
     cheap
    0.10
    easy
    0.10
    ç®Ģæĺĵ
    0.10
    æĺĵäºİ
    0.10
    ç®Ģåįķæĺĵ
    0.10
    Activations Density 0.381%

    No Known Activations