© 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. 38004
    Prev
    Next
    INDEX
    Explanations

    previously, normally, otherwise

    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
    çĭ¬çī¹çļĦ
    -0.11
    æĿŃ
    -0.09
    注æĺİæĿ¥æºIJ
    -0.09
    羣å®ŀçļĦ
    -0.09
    æī£
    -0.09
    èݼ
    -0.08
    .pres
    -0.08
    åĩij
    -0.08
    Segue
    -0.08
    çIJ¢
    -0.08
    POSITIVE LOGITS
    åģļçļĦäºĭæĥħ
    0.11
    纷纷
    0.10
    æİ·
    0.09
    OPTIONS
    0.09
    _wf
    0.09
    ADM
    0.09
     ÑĢанее
    0.08
    åıªä¸įè¿ĩæĺ¯
    0.08
    ä¸įè¿ĩæĺ¯
    0.08
     elsewhere
    0.08
    Activations Density 0.093%

    No Known Activations