© 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. 58031
    Prev
    Next
    INDEX
    Explanations

    checks and ACH

    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
    ä¸įæľį
    -0.07
    åĪĨéħįåĪ°
    -0.07
    zey
    -0.07
    æ¦
    -0.07
    ä¸įå¿ĺ
    -0.07
    elix
    -0.06
    çĿ¦
    -0.06
    /licenses
    -0.06
    丽èİİ
    -0.06
    .gg
    -0.06
    POSITIVE LOGITS
    æī¿åħij
    0.11
    票æį®
    0.09
    æ±ĩ票
    0.09
    妥åĸĦä¿Ŀ管
    0.08
    转贴
    0.08
    èĥĮ书
    0.08
     issued
    0.08
     endorsement
    0.08
    Authenticated
    0.08
     Scotia
    0.08
    Activations Density 0.009%

    No Known Activations