© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9655
    Prev
    Next
    INDEX
    Explanations

    beta software versions

    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
    umm
    -0.10
    ../../../
    -0.10
    ../
    -0.09
    åIJ¸
    -0.09
    me
    -0.08
    ä¸ĸ家
    -0.08
    ÑĮ
    -0.08
    orate
    -0.08
    ãģıãĤĭ
    -0.08
    åĢ¡
    -0.08
    POSITIVE LOGITS
    izr
    0.10
    åIJijå¤ĸ
    0.09
    æľŁéĹ´
    0.09
    æ´®
    0.09
    .beta
    0.09
    (beta
    0.09
     incom
    0.09
    ted
    0.09
     Introduced
    0.09
    çīĸ
    0.09
    Activations Density 0.033%

    No Known Activations