© 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. 3717
    Prev
    Next
    INDEX
    Explanations

    asdf or numbers followed by tokens

    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
    è´
    -0.10
    åºĦ
    -0.09
    赦
    -0.09
    æį©
    -0.09
    .Arg
    -0.09
    èİĬ
    -0.09
    åİī
    -0.09
    ä½łä»¥ä¸º
    -0.09
    aires
    -0.08
     Axe
    -0.08
    POSITIVE LOGITS
    饯
    0.10
    ult
    0.10
    oid
    0.09
    ulti
    0.09
    ultimate
    0.09
    ä¸į管
    0.09
    åīį线
    0.09
    æĪĸå¤ļ
    0.08
    oids
    0.08
    ãģĿãģĨãģ§ãģĻ
    0.08
    Activations Density 0.102%

    No Known Activations