© 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. 3573
    Prev
    Next
    INDEX
    Explanations

    sun microsystems, sun tanning, sun staff

    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
    çĤ¬
    -0.10
    .gmail
    -0.09
    ä¼Ĺ
    -0.09
    åľľ
    -0.09
    èºģ
    -0.09
    PRI
    -0.09
    oss
    -0.09
    æµĨ
    -0.09
    æ²¾
    -0.08
    æĶ¯æĴij
    -0.08
    POSITIVE LOGITS
    åĢ¦
    0.09
    ;base
    0.09
    ä¸ĢåĪĻ
    0.08
    از
    0.08
    åij³
    0.08
     Vect
    0.08
    lus
    0.08
    å·¢
    0.08
     Seah
    0.08
    å¤ķ
    0.08
    Activations Density 0.015%

    No Known Activations