© 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. 42714
    Prev
    Next
    INDEX
    Explanations

    data editing and storage

    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
    mgr
    -0.08
    vf
    -0.07
    åĢ¼å¾Ĺä¸ĢæıIJ
    -0.07
    odz
    -0.07
     Phillip
    -0.07
    eshire
    -0.07
    ÙĦاÙħ
    -0.07
    彦
    -0.07
    ä¸ĭæīĭ
    -0.07
    Interpolator
    -0.07
    POSITIVE LOGITS
    linger
    0.07
     itd
    0.07
    çĤ«
    0.07
    âĦ¢
    0.06
     THEN
    0.06
     '\
    0.06
    å¦Ĥçİī
    0.06
    æĺ¯å¤ļä¹Ī
    0.06
    ä¾Ŀæ³ķä¾Ŀè§Ħ
    0.06
    ~~
    0.06
    Activations Density 0.050%

    No Known Activations