© 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. 4397
    Prev
    Next
    INDEX
    Explanations

    endings in -ic, -ology, -al

    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
    åºķå±Ĥ
    -0.09
     вÑĢемен
    -0.09
    夫人
    -0.08
     suites
    -0.08
    æİİ
    -0.08
     اÙĦصØŃ
    -0.08
    ä¸ºçĽ®æłĩ
    -0.08
     vg
    -0.08
    ä¸įéĢĤåIJĪ
    -0.08
    massage
    -0.08
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.11
    æĦıä¹īä¸Ĭ
    0.10
    åIJİæŀľ
    0.10
    åŃ³
    0.09
    é¹Ħ
    0.09
    åŁ
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
     context
    0.09
    _userid
    0.09
    æĢ»åħ¬åı¸
    0.09
    Activations Density 0.636%

    No Known Activations