© 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. 48680
    Prev
    Next
    INDEX
    Explanations

    American States, Columbus Day

    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
     Lam
    -0.10
    éĺ´éĺ³
    -0.10
    åľ¨å®¶
    -0.09
    ¹Ħ
    -0.09
    èĢĮåİ»
    -0.09
    wer
    -0.08
    示èĮĥåĮº
    -0.08
    è·ijéģĵ
    -0.08
    å±ħ家
    -0.08
    WER
    -0.08
    POSITIVE LOGITS
    æŁ¥çľĭæĽ´å¤ļ
    0.09
    èįĩ
    0.09
    童年
    0.09
    西çĶ²
    0.09
    ä¸įä¸ĭ
    0.09
     cú
    0.09
     EXTRA
    0.09
     Paras
    0.09
     Specs
    0.09
    åĪº
    0.09
    Activations Density 0.067%

    No Known Activations