© 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. 30170
    Prev
    Next
    INDEX
    Explanations

    Names followed by titles or descriptions

    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
    è´µ
    -0.12
    è²´
    -0.09
    uset
    -0.08
    ãģĮãģĭ
    -0.08
    温室
    -0.08
    è¡·å¿ĥ
    -0.08
    æłijæľ¨
    -0.08
    å¦ĤæľŁ
    -0.08
    itt
    -0.07
    à¹Ģà¸Ĺà¸ŀ
    -0.07
    POSITIVE LOGITS
    éĺĶ
    0.12
    å¸Ŀ
    0.11
    asar
    0.10
    åĸĺ
    0.10
    çĽ¥
    0.09
    Ñĥнк
    0.09
    è¾ħ
    0.09
    IDL
    0.09
    çıIJ
    0.09
    ì»´
    0.09
    Activations Density 0.038%

    No Known Activations