© 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. 3281
    Prev
    Next
    INDEX
    Explanations

    surface of body parts

    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
    è¦ģä¹Ī
    -0.06
    çľ¼åīį
    -0.06
     Mid
    -0.06
    åľ¨èĦ¸ä¸Ĭ
    -0.06
    æŁIJç§į
    -0.06
    Either
    -0.06
    æĶ¹åıĺäºĨ
    -0.06
    based
    -0.06
    zew
    -0.06
     succeeding
    -0.06
    POSITIVE LOGITS
    çŃīå¤Ħ
    0.10
     areas
    0.10
    çŃīéĩįçĤ¹
    0.09
    areas
    0.09
    è¿ĻäºĽåľ°æĸ¹
    0.09
    åıĬåij¨è¾¹
    0.09
    ä¸īåĮº
    0.09
    æĤ£å¤Ħ
    0.09
    ä¸Ģéģį
    0.08
    é¡½åĽº
    0.08
    Activations Density 0.086%

    No Known Activations