© 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. 32180
    Prev
    Next
    INDEX
    Explanations

    station names and email addresses

    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
    ettle
    -0.10
    åħ¨åªĴä½ĵ
    -0.10
    è¾ķ
    -0.10
    çīº
    -0.10
    tti
    -0.10
    æĴ©
    -0.09
    /export
    -0.09
    åĤį
    -0.08
    åIJij社ä¼ļ
    -0.08
    uele
    -0.08
    POSITIVE LOGITS
    楼ä¸ĭ
    0.11
    æijĶ
    0.11
    -fed
    0.10
    糸
    0.09
    é«ĺ楼
    0.09
     frag
    0.09
    ç¨Ķ
    0.09
     fed
    0.09
     height
    0.09
    æĴij
    0.09
    Activations Density 0.075%

    No Known Activations