© 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. 3315
    Prev
    Next
    INDEX
    Explanations

    query string or arguments

    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
    è½»
    -0.26
    å¤§åĽ½
    -0.25
    wing
    -0.24
    ParallelGroup
    -0.24
    deen
    -0.24
     Silicon
    -0.24
    cuda
    -0.23
     fluffy
    -0.23
     pockets
    -0.22
     ASTM
    -0.22
    POSITIVE LOGITS
     URL
    0.44
    URL
    0.40
     url
    0.37
     URLs
    0.35
     urlencode
    0.35
    (URL
    0.33
     URI
    0.33
    QueryString
    0.32
    	url
    0.32
     "?
    0.32
    Activations Density 0.569%

    No Known Activations