© 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. 3108
    Prev
    Next
    INDEX
    Explanations

    places and states

    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
    Not in Any Lists

    No Comments

    Negative Logits
     underwater
    -0.25
    æĮªå¨ģ
    -0.25
    æµ·æ°´
    -0.24
     ocean
    -0.23
    çĿģ
    -0.23
    rog
    -0.23
    Bel
    -0.23
    çľģæķĻèĤ²åİħ
    -0.22
    Exec
    -0.22
     Underground
    -0.21
    POSITIVE LOGITS
    åŁİ
    0.29
    миÑĢ
    0.28
    ä¸Ģ座
    0.28
    èģĨåIJ¬
    0.25
    æĺ¯ä¸Ģ座
    0.25
     streets
    0.24
     broadcasts
    0.23
     STREET
    0.23
    éĤij
    0.23
     Broadcast
    0.23
    Activations Density 0.007%

    No Known Activations