© 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. 37674
    Prev
    Next
    INDEX
    Explanations

    equal or similar concepts

    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
    Negative Logits
    REEN
    -0.09
    luss
    -0.08
    _ONCE
    -0.08
    ç»Ī
    -0.08
    çĤ¬
    -0.07
    èĬŃ
    -0.07
    ingss
    -0.07
    lte
    -0.07
    æī
    -0.07
    lus
    -0.07
    POSITIVE LOGITS
    (equal
    0.09
     equal
    0.08
    equal
    0.08
     ÑĢав
    0.07
     igual
    0.07
    大åIJĮ
    0.07
    å¹³çŃīçļĦ
    0.07
     Equal
    0.07
    å¹³çŃī
    0.07
    ä¸Ģèµ·åĪĨ享
    0.07
    Activations Density 0.066%

    No Known Activations