© 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. 50018
    Prev
    Next
    INDEX
    Explanations

    competitions, awards, shows, conferences

    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
    bo
    -0.09
    éħ·
    -0.08
    hir
    -0.08
    æ¶Įçİ°åĩº
    -0.08
     deputies
    -0.08
    lier
    -0.08
    ÑħÑĢан
    -0.08
    å¾ĺå¾Ĭ
    -0.08
    çļĦä¸Ģ款
    -0.08
    åľ¨è¿ĩåİ»
    -0.08
    POSITIVE LOGITS
    ãĤªãĤ¹
    0.10
    ione
    0.10
    诸å¦Ĥ
    0.10
    ä¾ĭå¦Ĥ
    0.10
    expo
    0.09
    æľºæŀĦ
    0.09
    æ¯Ķå¦Ĥ
    0.09
    exter
    0.09
    çĪ±ä½ł
    0.09
    ä½łçİ°åľ¨
    0.09
    Activations Density 0.305%

    No Known Activations