© 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. 31533
    Prev
    Next
    INDEX
    Explanations

    amazon.com, inc. or its affiliates

    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
    æĿŃ
    -0.12
    çŀĴ
    -0.11
    æµģ失
    -0.11
    éĤ°
    -0.09
    realm
    -0.09
    çļĦ主é¢ĺ
    -0.09
    主é¢ĺ
    -0.09
    åĽŀåįĩ
    -0.08
    主ä½ĵ
    -0.08
    ksz
    -0.08
    POSITIVE LOGITS
    Amazon
    0.15
     Amazon
    0.14
    .amazon
    0.14
    /aws
    0.14
    äºļ马éĢĬ
    0.13
    .amazonaws
    0.12
    amazon
    0.12
    .AWS
    0.11
     amazon
    0.11
     Alexa
    0.10
    Activations Density 0.192%

    No Known Activations