© 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. 53818
    Prev
    Next
    INDEX
    Explanations

    World, Kats, space, pony, Tuning, NetBSD

    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
    åħ¥å¢ĥ
    -0.09
    æĥħ人
    -0.08
    .jav
    -0.08
    ä¸įé«ĺ
    -0.08
    å¢Ļä¸Ĭ
    -0.08
    rice
    -0.08
    åħ¥
    -0.08
    åı¯æĥ³èĢĮçŁ¥
    -0.08
    çŀ³
    -0.08
    RON
    -0.08
    POSITIVE LOGITS
    åıĤ
    0.10
    æĹĭ
    0.10
    æĿijæ°ij们
    0.10
    åį¯
    0.10
    çļĦåľŁåľ°
    0.09
    æĮ
    0.09
    åľ£è¯ŀ
    0.09
     towns
    0.09
    èļ
    0.09
    åĴĮåľ°åĮº
    0.09
    Activations Density 0.110%

    No Known Activations