© 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. 51358
    Prev
    Next
    INDEX
    Explanations

    design and creation

    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
    çĦ¶æĺ¯
    -0.11
    aneous
    -0.10
    itta
    -0.10
    edes
    -0.09
    ìĭľíĤ¤
    -0.09
    een
    -0.09
    asar
    -0.09
     знаÑĩ
    -0.09
    æģĵ
    -0.08
    çĸ¹
    -0.08
    POSITIVE LOGITS
    åĬłçĽŁåºĹ
    0.09
    sons
    0.09
    é¦Ķ
    0.09
    urations
    0.08
    åĩºåħ¥
    0.08
     Tos
    0.08
    çѵ
    0.08
    ultan
    0.08
    ANTE
    0.08
    诬
    0.08
    Activations Density 0.056%

    No Known Activations