© 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. 30828
    Prev
    Next
    INDEX
    Explanations

    NEWS, Blog, :

    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¸ĢåĽ¢
    -0.11
    åŃĶéĽĢ
    -0.10
    åį¡çīĩ
    -0.09
     ho
    -0.09
    ä¿Ŀå®ļ
    -0.09
    .shtml
    -0.09
    ä¸įèµ·
    -0.09
    æķıéĶIJ
    -0.09
    æİ°
    -0.09
    ordo
    -0.08
    POSITIVE LOGITS
    æĴķ
    0.09
     interrog
    0.09
    å°§
    0.09
     Vern
    0.08
    å±ł
    0.08
    çĥŁèįī
    0.08
    å¨ģå°¼æĸ¯
    0.08
    累累
    0.08
    æĸ©
    0.08
     italian
    0.08
    Activations Density 0.107%

    No Known Activations