© 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. 47912
    Prev
    Next
    INDEX
    Explanations

    plateau, backdrop, remote, end, Dawson, high, Copyright

    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
    adem
    -0.09
     Jersey
    -0.09
    æĺŁåº§
    -0.09
    avar
    -0.08
    {{{
    -0.08
    ç²ĺ
    -0.08
    enko
    -0.08
    夹
    -0.08
     rever
    -0.08
    ç«Ļ
    -0.08
    POSITIVE LOGITS
    çĸĨ
    0.10
    çī¹æ®ĬçļĦ
    0.10
    æģķ
    0.10
    è°ĥåĬ¨
    0.10
    é«ĺåİŁ
    0.10
    æĭīæĸ¯
    0.10
    举åĬŀçļĦ
    0.09
    çĥŃ带
    0.09
    æ¤Ĵ
    0.09
    ÑĤол
    0.09
    Activations Density 0.113%

    No Known Activations