© 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. 44624
    Prev
    Next
    INDEX
    Explanations

    replying to

    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
    indsight
    -0.08
    geschrieben
    -0.08
    abu
    -0.07
    iership
    -0.07
    falen
    -0.07
    ölcs
    -0.07
    lire
    -0.07
    atezza
    -0.07
    ÑģÑĤиÑĤ
    -0.07
    ìķ
    -0.06
    POSITIVE LOGITS
    çŃĶå¤į
    0.12
    åĽŀåºĶ
    0.12
    à¸ķà¸Ńà¸ļ
    0.11
    çļĦåĽŀçŃĶ
    0.10
     responses
    0.10
    åºĶçŃĶ
    0.10
     replies
    0.10
    /response
    0.10
     trả
    0.10
     Responses
    0.10
    Activations Density 0.057%

    No Known Activations