© 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. 22175
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and tags

    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
    adol
    -0.10
    ãĥ£
    -0.09
    æĥij
    -0.09
    è¡ĮåĪĹ
    -0.08
    moth
    -0.08
    inha
    -0.08
    noc
    -0.08
    ä¸įäºĨ
    -0.08
    寮
    -0.08
    éĻ¨
    -0.08
    POSITIVE LOGITS
    ฯ
    0.11
    implicitly
    0.08
    åı¯è¡Į
    0.08
    fait
    0.08
    gether
    0.08
    ean
    0.08
    éĴĪ
    0.08
    人éĻħåħ³ç³»
    0.08
    æľīçĤ¹
    0.08
    нÑĮ
    0.07
    Activations Density 2.321%

    No Known Activations