© 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. 11840
    Prev
    Next
    INDEX
    Explanations

    lavender, lava, avo

    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
    çĦ¶æĺ¯
    -0.13
     khÄĥn
    -0.11
    ãģĺ
    -0.10
     ÑĢазвиÑĤие
    -0.10
    abet
    -0.10
    ÙħاÙĨ
    -0.10
    éħIJ
    -0.09
    稳å®ļæĢ§
    -0.09
    æ¡ł
    -0.08
    sWith
    -0.08
    POSITIVE LOGITS
    holm
    0.10
    å¢Ģ
    0.09
    ays
    0.09
    asting
    0.09
    irth
    0.09
    èĮ
    0.09
    ucher
    0.09
    éĺ¡
    0.08
    濯
    0.08
    legation
    0.08
    Activations Density 0.010%

    No Known Activations