© 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. 53270
    Prev
    Next
    INDEX
    Explanations

    Printer problems and fixes

    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
    设计çIJĨ念
    -0.10
    严谨
    -0.09
    çѱ
    -0.09
    åĺĺ
    -0.09
    çĽijè§Ĩ
    -0.08
    éĤ£äºº
    -0.08
    ä¸ŃåIJ«æľī
    -0.08
    åģļçļĦäºĭæĥħ
    -0.08
    ä¸į符åIJĪ
    -0.08
    .aw
    -0.08
    POSITIVE LOGITS
     troub
    0.10
    ç»´ä¿®
    0.09
    诺
    0.09
    çķ´
    0.09
     troubleshooting
    0.08
    æµ·å°Ķ
    0.08
    çªģåĩºéĹ®é¢ĺ
    0.08
    iej
    0.08
    纳
    0.08
    åı¯èĥ½åĩºçİ°
    0.08
    Activations Density 0.280%

    No Known Activations