© 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. 3362
    Prev
    Next
    INDEX
    Explanations

    Gall, gallium, gallamine

    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
    รา
    -0.21
    ãģĹãģ¾ãģĨ
    -0.19
    ìĬ¨
    -0.18
    verse
    -0.18
    æĿ¥åĽŀ
    -0.18
    unal
    -0.18
    ĺ
    -0.18
    éĻIJãĤĬ
    -0.17
    bers
    -0.17
    actly
    -0.17
    POSITIVE LOGITS
    ers
    0.25
    ingly
    0.24
    æ®Ĩ
    0.22
    ened
    0.21
    enger
    0.20
    iday
    0.20
    iola
    0.20
    ertext
    0.20
    ERS
    0.20
    uil
    0.20
    Activations Density 0.024%

    No Known Activations