© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4548
    Prev
    Next
    INDEX
    Explanations

    -like descriptor

    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
    OrDefault
    -0.07
    uts
    -0.07
    isser
    -0.06
    æ¯ıä¸Ģ天
    -0.06
    åıªè¦ģæľī
    -0.06
    ord
    -0.06
    atters
    -0.06
    çĹħåºĬ
    -0.06
    LEX
    -0.06
    1
    -0.06
    POSITIVE LOGITS
    -like
    0.12
    èĪ¬çļĦ
    0.12
    ä¸Ģæł·çļĦ
    0.10
    èĪ¬åľ°
    0.10
    ä¼¼çļĦ
    0.10
    å¼ıçļĦ
    0.10
    çĬ¶çļĦ
    0.09
    çĬ¶
    0.09
    èĪ¬
    0.09
    подоб
    0.09
    Activations Density 0.120%

    No Known Activations