© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3235
    Prev
    Next
    INDEX
    Explanations

    exit or return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    _Rect
    -0.23
    ilon
    -0.23
    gart
    -0.23
    åIJĦè¡ĮåIJĦ
    -0.23
    .Disclaimer
    -0.22
    getParam
    -0.22
     SEAL
    -0.21
    mith
    -0.21
    urf
    -0.21
     GRAT
    -0.20
    POSITIVE LOGITS
     break
    0.30
    throw
    0.28
     throw
    0.28
    	throw
    0.28
     clearInterval
    0.27
     return
    0.25
    	return
    0.25
     fatalError
    0.25
    abort
    0.24
    	break
    0.24
    Activations Density 0.510%

    No Known Activations