© 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. 48961
    Prev
    Next
    INDEX
    Explanations

    link, chain, or convert

    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
    å½ĵåħ¶
    -0.08
     hervor
    -0.08
    signature
    -0.08
    lings
    -0.07
     screenings
    -0.07
    æľªæĮīè§Ħå®ļ
    -0.07
    æĹ¶è¡¨ç¤º
    -0.07
     comport
    -0.06
    kins
    -0.06
    æĶ¯
    -0.06
    POSITIVE LOGITS
    éĹ´æİ¥
    0.09
     chained
    0.08
    éĵ¾æİ¥
    0.08
     chaining
    0.08
    ä¸ŃéĹ´
    0.08
     indire
    0.08
     indirect
    0.08
    LINK
    0.08
     linking
    0.08
    link
    0.08
    Activations Density 0.029%

    No Known Activations