© 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. 1026
    Prev
    Next
    INDEX
    Explanations

    said and done

    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
     Reply
    -0.09
     Freed
    -0.09
    alen
    -0.09
    ÙĩØ©
    -0.08
    \Block
    -0.08
    çģĮ
    -0.08
    à¸Ĭา
    -0.08
    ill
    -0.08
    วย
    -0.08
    elles
    -0.08
    POSITIVE LOGITS
    æľĢç»Ī
    0.13
    æľĢçµĤ
    0.11
    æľĢåIJİ
    0.11
     ultimately
    0.10
     Orb
    0.10
    åħ·ä½ĵåĨħ容
    0.10
     final
    0.10
     finally
    0.10
    ç»Ī
    0.10
    鹫
    0.10
    Activations Density 0.035%

    No Known Activations