© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    replace or change

    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
    ä¸ĢæĹ¦è¢«
    -0.08
    upa
    -0.07
    ASE
    -0.06
    åľ¨ä½¿çĶ¨
    -0.06
    Chu
    -0.06
    ä¸ĢæŦ
    -0.06
     wider
    -0.06
     Brunswick
    -0.05
    eru
    -0.05
    detach
    -0.05
    POSITIVE LOGITS
    æį¢æĪIJ
    0.14
    æĶ¹ä¸º
    0.12
    åıĸèĢĮ代ä¹ĭ
    0.11
     Replace
    0.10
    æĽ¿æį¢
    0.10
    èĢĮ代ä¹ĭ
    0.10
    æĶ¹æĪIJ
    0.10
     вмеÑģÑĤо
    0.10
     ÐĴмеÑģÑĤо
    0.10
     замениÑĤÑĮ
    0.09
    Activations Density 0.153%

    No Known Activations