© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8914
    Prev
    Next
    INDEX
    Explanations

    quantities or comparisons

    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
    velt
    -0.10
    1
    -0.09
    6
    -0.08
    æ¶Į
    -0.08
    ä¼łåĩº
    -0.08
     Scarlett
    -0.08
    å¹´éĻIJ
    -0.08
    æ·Ħ
    -0.08
    9
    -0.07
    HAM
    -0.07
    POSITIVE LOGITS
    éĶ¢
    0.10
    æĪijå°±
    0.10
    estation
    0.10
    ackets
    0.09
    ä¸į失
    0.09
    há»ķ
    0.09
    æģ¬
    0.09
    èªĬ
    0.09
    ä»İæľª
    0.09
    çĥĿ
    0.09
    Activations Density 0.087%

    No Known Activations