© 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. 51063
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    éĤ£æł·çļĦ
    -0.11
     обÑĥÑĩениÑı
    -0.09
    è°´
    -0.09
    acr
    -0.09
     Corona
    -0.09
    ÐľÐĺ
    -0.09
    ç§ĥ
    -0.09
    rette
    -0.09
    éĤ£ä»½
    -0.09
    emic
    -0.08
    POSITIVE LOGITS
     riv
    0.09
    æĢ»æĶ¶åħ¥
    0.09
    åĪ°åºķæĺ¯
    0.09
    究竣æĺ¯
    0.09
    åĽºçĦ¶
    0.08
    ä¸Ģ缴æĺ¯
    0.08
     إذ
    0.08
    çĻ£
    0.08
    æĢ»ç®Ĺ
    0.08
    åĪ°åºķ
    0.07
    Activations Density 0.448%

    No Known Activations