© 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. 32496
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
    ä¸įå½±åĵį
    -0.09
    ucch
    -0.09
    aksi
    -0.08
    çĶŁæľº
    -0.08
    è§ľ
    -0.08
    æªĶ
    -0.08
    EDIT
    -0.08
    æŃ¥
    -0.08
    å©·
    -0.08
    anine
    -0.08
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.11
    оÑĩно
    0.10
    çºĮ
    0.09
    åIJĮä»ģ
    0.09
    æ»Ĥ
    0.09
    æ¶
    0.09
    çļ®
    0.09
     Wilmington
    0.09
    å±ij
    0.09
    åĩłå¼ł
    0.08
    Activations Density 0.065%

    No Known Activations