© 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. 32951
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

    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
    çļĦ好
    -0.10
    çļĦæĶ¿æ²»
    -0.09
    èĭ±æīį
    -0.09
    åı¦ä¸ĢåįĬ
    -0.09
    è·ijåİ»
    -0.09
    禺
    -0.09
    类产åĵģ
    -0.08
    èļĤ
    -0.08
    åĢĴæĺ¯
    -0.08
    çĻ¾å¼º
    -0.08
    POSITIVE LOGITS
     obr
    0.09
    çİ°åľº
    0.08
    afil
    0.08
    çı¾åł´
    0.08
     Microsystems
    0.08
    Dup
    0.08
     hog
    0.08
    è¦ģæĥ³
    0.08
    ightly
    0.08
     chuyá»ĩn
    0.08
    Activations Density 0.024%

    No Known Activations