© 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. 2972
    Prev
    Next
    INDEX
    Explanations

    enters into

    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
    åºı
    -0.10
    åĻİ
    -0.09
    STER
    -0.09
    åĩºå¢ĥ
    -0.09
     Bundy
    -0.09
    ster
    -0.09
    åĶĨ
    -0.09
    åĩºå±Ģ
    -0.09
    æŀ¯
    -0.08
    baugh
    -0.08
    POSITIVE LOGITS
    ilty
    0.10
    ä¸ºæľŁ
    0.10
    éĺĹ
    0.09
    ç»ĵå®ŀ
    0.09
    åħ¬ç½ijå®īå¤ĩ
    0.09
    æĺĢ
    0.08
    æľ¬ç½ijç«Ļ
    0.08
    Ark
    0.08
    æĢİ
    0.08
    æĦıä¹ī
    0.08
    Activations Density 0.010%

    No Known Activations