© 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. 48355
    Prev
    Next
    INDEX
    Explanations

    not present or not included

    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
    æľīäºĨ
    -0.11
    ä¸ŃæĸŃ
    -0.10
    è¦ģæľī
    -0.10
    £¼
    -0.09
    æĹħ客
    -0.09
    ÑĢÑĥк
    -0.08
    _impl
    -0.08
    稽
    -0.08
    omnia
    -0.08
    ä¿İ
    -0.08
    POSITIVE LOGITS
    ä¸Ģæĸ¹
    0.10
    士
    0.09
    èݽ
    0.09
    å½ĵçĦ¶æĺ¯
    0.09
    æŃ¤æ¬¡
    0.09
     parach
    0.09
    个人è§ĤçĤ¹
    0.08
    ç»®
    0.08
    .stem
    0.08
    åįĹæĸ¹
    0.08
    Activations Density 0.029%

    No Known Activations