© 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. 3415
    Prev
    Next
    INDEX
    Explanations

    may be beneficial or suitable

    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
     fragmentation
    -0.27
     overlaps
    -0.24
     chlor
    -0.23
     rearr
    -0.23
    ä¸į说
    -0.22
    tÃł
    -0.22
     fragment
    -0.22
     scor
    -0.22
    edly
    -0.22
    rant
    -0.22
    POSITIVE LOGITS
    åı¯è¡Į
    0.48
    éĢĤåIJĪ
    0.44
    æľĢéĢĤåIJĪ
    0.40
    åIJĪéĢĤ
    0.39
    åĪĴç®Ĺ
    0.37
     suitable
    0.37
    éģ©åIJĪ
    0.36
     preferable
    0.35
    éĢĤåIJĪèĩªå·±
    0.35
     suitability
    0.35
    Activations Density 0.100%

    No Known Activations