© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12272
    Prev
    Next
    INDEX
    Explanations

    jolts shattering juggling blinding roiled mosh spate

    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
    Negative Logits
    neath
    -0.13
    oretical
    -0.12
    gether
    -0.11
    phalt
    -0.11
    empre
    -0.11
    è¿Ļå°±æĺ¯
    -0.10
    chaft
    -0.10
    ../../
    -0.09
    ãĤĬ
    -0.09
    otros
    -0.09
    POSITIVE LOGITS
    ä¼ĹæīĢ
    0.09
    åIJĪä½ľåħ³ç³»
    0.08
    æĺ
    0.08
    亲æĥħ
    0.08
    åľ°è¯´
    0.08
    æ¿Ģèµ·
    0.08
    åIJĪä¸Ģ
    0.08
    åĿļæĮģ以
    0.08
    äºĨä¸ĢäºĽ
    0.08
    åħ¨ä¸ĸçķĮ
    0.07
    Activations Density 0.290%

    No Known Activations