© 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. 45071
    Prev
    Next
    INDEX
    Explanations

    technical, academic, and clinical concepts

    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
     alike
    -0.08
    ä¹ĭéŁ³
    -0.08
    åħ¶æŀĹ
    -0.08
    apun
    -0.07
    ä»ħæѤ
    -0.07
    olim
    -0.07
    ÙģÙĪر
    -0.07
     Addr
    -0.07
    使å®ĥ
    -0.07
    为己任
    -0.07
    POSITIVE LOGITS
    æĺ¯æĮĩåľ¨
    0.08
    åıĪåı«
    0.08
    åıĪ称
    0.08
    egger
    0.07
    æĺ¯æĮĩ
    0.07
     refers
    0.07
    æĮĩçļĦæĺ¯
    0.07
    ä¹Łåı«
    0.07
    —a
    0.07
    åıĪåIJį
    0.06
    Activations Density 0.352%

    No Known Activations