© 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. 51339
    Prev
    Next
    INDEX
    Explanations

    after and

    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
    èķ´
    -0.07
     reportedly
    -0.07
    ÙıÙħÙĴ
    -0.06
    umpt
    -0.06
    å²ļ
    -0.06
    éĢļèĪª
    -0.06
    fox
    -0.06
    æºľæºľ
    -0.06
    ichel
    -0.06
    éĿĴéĿĴ
    -0.06
    POSITIVE LOGITS
    æĬķèµĦæĪĸ
    0.09
     then
    0.09
    çĦ¶åIJİåĨį
    0.09
     later
    0.08
     poi
    0.08
     luego
    0.08
     THEN
    0.08
     magari
    0.08
    åIJİç»Ń
    0.08
    çĦ¶åIJİåľ¨
    0.08
    Activations Density 0.090%

    No Known Activations