© 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. 2644
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

    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
    ä»ĸèĩªå·±
    -0.11
    èĩªå·±
    -0.09
    strand
    -0.09
    èĩªå·±çļĦ
    -0.09
    èĩªå®¶
    -0.09
     Victory
    -0.09
    itional
    -0.09
    buster
    -0.09
    èĩªèº«
    -0.08
    ford
    -0.08
    POSITIVE LOGITS
    zelf
    0.20
    verständlich
    0.15
    -même
    0.11
    ändig
    0.11
    ãģĩ
    0.10
    æĹİ
    0.10
     بÙĨÙģس
    0.10
    sing
    0.09
    Argb
    0.09
    elves
    0.09
    Activations Density 0.045%

    No Known Activations