© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3762
    Prev
    Next
    INDEX
    Explanations

    Saint/São followed by geographical names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ï¸ı
    -0.13
    itor
    -0.09
    elong
    -0.08
     sola
    -0.08
    Ħ
    -0.08
    ãģİ
    -0.08
    åħ¥åħļ
    -0.08
    éĥ¨å§Ķ
    -0.08
    æį
    -0.08
    ted
    -0.08
    POSITIVE LOGITS
    enance
    0.11
    ains
    0.10
    uess
    0.09
    使çĶ¨ç¶²è·¯
    0.09
    cry
    0.09
    åı¯æĥľ
    0.08
    å¾Ĵ
    0.08
    ฯ
    0.08
    atile
    0.08
    -root
    0.08
    Activations Density 0.014%

    No Known Activations