© 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. 10201
    Prev
    Next
    INDEX
    Explanations

    observed phenomena or states

    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
    ä¼ļæľīå¾Īå¤ļ
    -0.07
    å±ĬæŶ
    -0.07
    /archive
    -0.07
     endowed
    -0.06
    à¸IJาà¸Ļะ
    -0.06
    åĤĺ
    -0.06
    hur
    -0.06
     sok
    -0.06
    åĩŃåĢŁåħ¶
    -0.06
    abbreviation
    -0.06
    POSITIVE LOGITS
     observed
    0.11
    è¿Ļ表æĺİ
    0.10
    表æĺİ
    0.09
     наблÑİдаеÑĤÑģÑı
    0.09
     unusually
    0.09
     unexpected
    0.09
    è¿Ļ说æĺİ
    0.08
    ç»ĵæŀľè¡¨æĺİ
    0.08
     unexpectedly
    0.08
    á»įc
    0.08
    Activations Density 0.042%

    No Known Activations