© 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. 31975
    Prev
    Next
    INDEX
    Explanations

    ocean

    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
    TING
    -0.10
    abouts
    -0.09
    leton
    -0.09
    lep
    -0.09
    TION
    -0.09
    ìŀ¥ìĿĦ
    -0.09
    -paying
    -0.09
    bole
    -0.09
     Lange
    -0.08
    çİ°å®ŀçĶŁæ´»
    -0.08
    POSITIVE LOGITS
    ized
    0.10
    æ·±å¤Ħ
    0.10
    Łèĥ½
    0.10
    à¹Į
    0.10
    ide
    0.10
    phans
    0.09
    wide
    0.09
    çĦ¶æĺ¯
    0.09
    ographic
    0.09
    æĢĢæĬ±
    0.09
    Activations Density 0.010%

    No Known Activations