© 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. 23133
    Prev
    Next
    INDEX
    Explanations

    Germanic and Romance given names, surnames, and place 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
    éĢĴ
    -0.09
    ç²½
    -0.08
     Berm
    -0.08
    å½°
    -0.08
    讳
    -0.08
    sett
    -0.08
    ampa
    -0.08
    ü
    -0.07
    çļĦä¸ĢéĿ¢
    -0.07
    éĢıè¿ĩ
    -0.07
    POSITIVE LOGITS
    å§Ķå±Ī
    0.11
     обÑĥÑĩ
    0.09
    åĪĿå¿ĥ
    0.09
    该项
    0.09
    çŃĶçĸij
    0.09
    ationale
    0.09
    retry
    0.08
    ש×Ŀ
    0.08
    gmt
    0.08
    .onNext
    0.08
    Activations Density 0.245%

    No Known Activations