© 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. 33962
    Prev
    Next
    INDEX
    Explanations

    FIG. is a

    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
    nero
    -0.08
    çŁ¥éģĵåIJĹ
    -0.07
    æĹ¥è®¯
    -0.07
    ä¸įä¹ħçļĦå°ĨæĿ¥
    -0.07
    éĨīäºĨ
    -0.07
    ׼×Ļ
    -0.07
    å¨ģå°Ķ
    -0.07
    heus
    -0.07
    odle
    -0.07
    åĵĪå°Ķ
    -0.07
    POSITIVE LOGITS
    èģĺ
    0.07
    ivor
    0.06
    æĭĶ
    0.06
     particulars
    0.06
    ä¸īåľ°
    0.06
    éĩĩ
    0.06
    æĸ°å¹´
    0.06
    resents
    0.06
    landers
    0.06
    askets
    0.05
    Activations Density 0.007%

    No Known Activations