© 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. 39260
    Prev
    Next
    INDEX
    Explanations

    a followed by a noun

    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
    ness
    -0.07
    antie
    -0.07
    uur
    -0.07
    ation
    -0.07
    nv
    -0.06
    stroke
    -0.06
     meisten
    -0.06
    çľĭåĪ°è¿Ļ个
    -0.06
    åĶ¾
    -0.06
    rolley
    -0.06
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.11
    è¯Ħä»·ä½ĵç³»
    0.09
    åıĪä¸Ģ个
    0.08
    elių
    0.08
    个æĪĸå¤ļ个
    0.07
    æľįåĬ¡ä½ĵç³»
    0.07
    æĪĸå¤ļ
    0.07
     multi
    0.07
    ä¸ĵå®¶åĽ¢éĺŁ
    0.07
    çĽijæİ§ç³»ç»Ł
    0.07
    Activations Density 0.637%

    No Known Activations