© 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. 52662
    Prev
    Next
    INDEX
    Explanations

    kick and variants

    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
    неÑĨ
    -0.09
    åĶĩ
    -0.09
     Fors
    -0.08
     Lans
    -0.08
     mos
    -0.08
    竹
    -0.08
    è·³è·ĥ
    -0.08
     Bard
    -0.08
    æŁIJä¸Ģ
    -0.08
     lips
    -0.08
    POSITIVE LOGITS
    ä½Ĩæĺ¯åľ¨
    0.09
    gren
    0.09
    æĿĤçī©
    0.09
    涧
    0.09
    ä¸ĢèĦļ
    0.09
    éħ°
    0.09
    èĨı
    0.09
     joe
    0.08
    ItemAt
    0.08
    è¶ħè¿ĩäºĨ
    0.08
    Activations Density 0.004%

    No Known Activations