© 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. 22371
    Prev
    Next
    INDEX
    Explanations

    digital signals

    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
    innie
    -0.06
    dech
    -0.06
    older
    -0.06
    æľ¬å°±
    -0.06
    erring
    -0.06
    achable
    -0.06
     Allo
    -0.06
    RICT
    -0.06
     Exists
    -0.06
    engt
    -0.06
    POSITIVE LOGITS
     tadi
    0.13
    ä¸Ĭè¿°
    0.11
    åĪļæīį
    0.09
    å¦Ĥä¸Ĭ
    0.09
    å¾ĹåĪ°çļĦ
    0.08
     identified
    0.08
    ä¸Ĭè¿°äºĭå®ŀ
    0.08
     obtained
    0.07
    æį¢æĿ¥çļĦ
    0.07
     aforementioned
    0.07
    Activations Density 0.126%

    No Known Activations