© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20101
    Prev
    Next
    INDEX
    Explanations

    writing emails

    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
    交æİ¥
    -0.10
     quán
    -0.09
    å²Ń
    -0.09
    端æŃ£
    -0.09
    _outputs
    -0.08
    .mas
    -0.08
    æĪ¾
    -0.08
    CALE
    -0.08
    oven
    -0.08
    éĢĢ
    -0.08
    POSITIVE LOGITS
    èĩ´çĶµ
    0.14
    èģĶç³»
    0.11
    éĹ®åĢĻ
    0.11
    ç¦Ģ
    0.10
    èģĶç³»æĪij们
    0.10
    mailto
    0.10
    æ¼ĵ
    0.10
    询éĹ®
    0.10
    询
    0.10
    åĤ¬
    0.09
    Activations Density 0.057%

    No Known Activations