© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11166
    Prev
    Next
    INDEX
    Explanations

    growth and rates

    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
    alach
    -0.08
    jist
    -0.07
    å¤ļä¸ªåĽ½å®¶åĴĮåľ°åĮº
    -0.07
    oglio
    -0.06
    perm
    -0.06
    åģ¥åº·å¿«ä¹IJ
    -0.06
    人åıĹ伤
    -0.06
    commended
    -0.06
    å¤ļå¤Ħ
    -0.06
    è¦ģç´§
    -0.06
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.21
    æĪĸä¸į
    0.19
    æĪĸ
    0.16
    æĪĸ缺
    0.15
    æĪĸå°ij
    0.14
    /-
    0.14
    หรืà¸Ńà¹Ħมà¹Ī
    0.14
    æĪĸæľª
    0.14
    /from
    0.14
    æĪĸéĿŀ
    0.14
    Activations Density 0.319%

    No Known Activations