© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    independent consultants

    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
    xcf
    -0.26
     Newsletter
    -0.25
     newsletters
    -0.24
    ãĥįãĤ¿
    -0.23
    Outlet
    -0.23
    éħİ
    -0.23
     ROUT
    -0.23
    zon
    -0.23
    åĨĴ
    -0.22
    Foreground
    -0.22
    POSITIVE LOGITS
    åħ¬æŃ£
    0.44
     impartial
    0.43
    éªĮ
    0.40
    çĭ¬ç«ĭ
    0.36
     appointed
    0.31
    ä¸ĵéŨ
    0.31
    çĽij
    0.31
     назнаÑĩен
    0.30
    çĽijçĿ£
    0.30
    第ä¸īæĸ¹
    0.30
    Activations Density 0.024%

    No Known Activations