© 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. 16710
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    åĩ«
    -0.11
    å®īåħ¨æĦŁ
    -0.10
    è¦ģæĥ³
    -0.10
    æĪIJ为ä¸Ģ个
    -0.09
    èĩªä¸»åĵģçīĮ
    -0.09
    ä»Ģä¹Īäºĭ
    -0.09
    åħ±åIJĮåıijå±ķ
    -0.09
    latin
    -0.09
    马ä¸Ĭå°±
    -0.08
    è¦ģæľī
    -0.08
    POSITIVE LOGITS
    è¿Ļä½į
    0.09
    åģļçļĦäºĭæĥħ
    0.09
    è¿IJä½ľ
    0.09
    ìħĢ
    0.09
    è¿Ľè¡ĮäºĨ
    0.08
    olis
    0.08
    yles
    0.08
    UNE
    0.08
    åı°ä¸Ĭ
    0.08
    åģļäºĨ
    0.08
    Activations Density 0.035%

    No Known Activations