© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    Avant Sports, Finewoods, Emerson's

    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
    ordo
    -0.10
    ç²³
    -0.08
    æħİéĩį
    -0.08
     tro
    -0.08
    tro
    -0.08
    è°¨æħİ
    -0.08
    apur
    -0.08
    andr
    -0.08
    è¯įæĿ¡
    -0.08
    oad
    -0.08
    POSITIVE LOGITS
    åĩºåĵģ
    0.14
    æݨåĩºçļĦ
    0.12
    éĤ£è¾¹
    0.11
    åİĤ家
    0.11
    åĵģçīĮçļĦ
    0.11
    家ä¼ģä¸ļ
    0.10
    åħ¬åı¸å°Ĩ
    0.10
    æĬĹèıĮ
    0.10
    éĽĨåĽ¢æĹĹä¸ĭ
    0.10
    åħ¬åı¸åľ¨
    0.10
    Activations Density 0.149%

    No Known Activations