© 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. 22216
    Prev
    Next
    INDEX
    Explanations

    the `the` `it` `there` `actually` `is` `has`

    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
    odiac
    -0.08
    edly
    -0.08
    बà¤Ĥध
    -0.07
    ÑĢаÑĤно
    -0.07
    åħ¶ä»ĸåľ°æĸ¹
    -0.07
    ÐŁÐ¸
    -0.07
    ç¥łåłĤ
    -0.07
     ÙĪÙĦÙĪ
    -0.07
    æĬĵç´§
    -0.07
    èݱ德
    -0.07
    POSITIVE LOGITS
    å½ĵä¸Ģ个
    0.08
    æľīåħ³äºİ
    0.07
    andy
    0.07
     Kamar
    0.06
    顾åIJįæĢĿä¹ī
    0.06
    
    0.06
    çħ§
    0.06
    é¦ĸåħĪéľĢè¦ģ
    0.06
    主è¦ģæľī
    0.06
    ï½ľ
    0.06
    Activations Density 0.056%

    No Known Activations