© 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. 16780
    Prev
    Next
    INDEX
    Explanations

    technical nouns and their contexts

    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
    åĿĬ
    -0.08
    -other
    -0.07
    AGMA
    -0.07
    ertools
    -0.07
    áĪĪ
    -0.07
    æĹ¥æĬ¥
    -0.07
    ikä
    -0.07
    ê°ģ
    -0.07
    åĴĮåħ¶ä»ĸ
    -0.06
    ëģĶ
    -0.06
    POSITIVE LOGITS
    Ī¬
    0.07
    çŃĶé¢ĺåį¡
    0.07
    åıĪä¸Ģ个
    0.07
    æĺ¯ä¸Ģéĥ¨
    0.07
    /apache
    0.07
    kat
    0.07
    ippo
    0.06
    å½ĵå½ĵ
    0.06
    æĪĸå¤ļ个
    0.06
     Ref
    0.06
    Activations Density 1.060%

    No Known Activations