© 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. 22467
    Prev
    Next
    INDEX
    Explanations

    notice things

    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
    лим
    -0.10
    æĪijçŁ¥éģĵ
    -0.10
    contro
    -0.09
    çľ¼çľĭ
    -0.09
    æĿĥ
    -0.09
    åĪ®
    -0.09
    大è§Ħ模
    -0.08
    ترÙĪ
    -0.08
    ?q
    -0.08
    ceeded
    -0.08
    POSITIVE LOGITS
    注æĦıåĪ°
    0.13
     notice
    0.09
    notice
    0.09
    antz
    0.09
    çĤ¹å¤ļ
    0.08
     noticed
    0.08
     remar
    0.08
    çݯå¢ĥä¸Ń
    0.08
    ä¹Łä¸įæĺ¯
    0.08
    eyer
    0.08
    Activations Density 0.044%

    No Known Activations