© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10276
    Prev
    Next
    INDEX
    Explanations

    PR related terms

    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
    uer
    -0.10
    颢
    -0.09
     гоÑģ
    -0.09
    å§Ķåī¯ä¹¦è®°
    -0.09
    æķķ
    -0.09
    лаÑĤ
    -0.09
    åħ¬åħ±èµĦæºIJ
    -0.09
    æ·±åĮĸæĶ¹éĿ©
    -0.09
    åħļå§Ķ书记
    -0.09
    вл
    -0.08
    POSITIVE LOGITS
    fully
    0.09
    (PR
    0.09
    æĦŁ
    0.08
    nod
    0.08
    æѤäºĭ
    0.08
     khá»ıi
    0.08
     caster
    0.08
    enti
    0.08
    adox
    0.08
     Fancy
    0.08
    Activations Density 0.009%

    No Known Activations