© 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. 5190
    Prev
    Next
    INDEX
    Explanations

    troublesome, persistent, nuisance

    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
    пиÑĤ
    -0.10
    è¡Į使
    -0.10
    æī¿åıĹ
    -0.09
    äºĴéĢļ
    -0.09
    æĨ¬
    -0.09
    çĶ¡
    -0.09
    æħİéĩį
    -0.08
    oplay
    -0.08
    æ½®
    -0.08
    大åĶIJ
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个éĹ®é¢ĺ
    0.11
     pes
    0.10
     bothering
    0.10
    çļĦéĹ®é¢ĺ
    0.10
    è¿ĺè®°å¾Ĺ
    0.10
    çĥ¦æģ¼
    0.10
    家ä¼Ļ
    0.10
    åĽ°æī°
    0.10
    çªģåĩºéĹ®é¢ĺ
    0.10
    çĥ¦
    0.09
    Activations Density 0.027%

    No Known Activations