© 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. 56196
    Prev
    Next
    INDEX
    Explanations

    see more, what, demo, http, Nic, Copyright

    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»ħ次äºİ
    -0.09
    ä»ij
    -0.09
    æĮīæŶ
    -0.09
    .hl
    -0.09
    éľĨ
    -0.09
    è¯ł
    -0.09
    æĪIJåIJį
    -0.08
    èµĸ以
    -0.08
    åľ¨æł¡
    -0.08
    à¹Ĥà¸Ħร
    -0.08
    POSITIVE LOGITS
    _derivative
    0.09
    们çļĦ
    0.09
    åħ·ä½ĵçļĦ
    0.09
    éĶ£
    0.08
    å¢ĥ
    0.08
     Morm
    0.08
    人åĬĽ
    0.08
    大å®Ĺ
    0.08
    mens
    0.08
    æī¿åĬŀ
    0.08
    Activations Density 0.009%

    No Known Activations