© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12362
    Prev
    Next
    INDEX
    Explanations

    not sure

    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
    Negative Logits
     zwar
    -0.15
    èĻ½çĦ¶
    -0.14
    éĽĸçĦ¶
    -0.12
    ãģ§ãģĻãģĮ
    -0.11
    ä½Ĩæĺ¯æĪij
    -0.11
    ä½Ĩå¦Ĥæŀľ
    -0.11
    èĻ½
    -0.11
    èĻ½è¯´
    -0.11
    çĦ¶
    -0.11
    éĽĸ
    -0.11
    POSITIVE LOGITS
    å°Ĩåħ¶
    0.11
    使ä¹ĭ
    0.09
     nonetheless
    0.09
    éĻ¤æѤä¹ĭå¤ĸ
    0.09
    åħ·ä½ĵåĨħ容
    0.09
    çļĦåħ·ä½ĵ
    0.09
    æĮĩå¼ķ
    0.09
    ä¸ĢèĤ¡
    0.09
    że
    0.08
    å¼ij
    0.08
    Activations Density 0.313%

    No Known Activations