© 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. 20166
    Prev
    Next
    INDEX
    Explanations

    text reconstruction, properties, explain

    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
    ç¯ģ
    -0.08
     attent
    -0.08
     Www
    -0.07
    going
    -0.07
    离ä¸įå¼Ģ
    -0.07
    çij·
    -0.07
    èģĶç½ij
    -0.07
     Shock
    -0.07
    æµĵæµĵ
    -0.07
    æĽ´å¼º
    -0.07
    POSITIVE LOGITS
    åľ¨çĶŁæ´»ä¸Ń
    0.11
    åĽłæŀľ
    0.10
    è¿Ĥ
    0.10
    _JO
    0.10
    ðł®
    0.10
     اÙĦاخبار
    0.10
    ç»ĻåĪ«äºº
    0.09
    æŃ¢æįŁ
    0.09
    人æ°ij群ä¼Ĺ
    0.09
    æķĮ人
    0.09
    Activations Density 0.127%

    No Known Activations