© 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. 3291
    Prev
    Next
    INDEX
    Explanations

    was born or started

    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
    å¾Ĵ
    -0.09
    æķħ
    -0.08
    æ³ļ
    -0.08
    OOK
    -0.08
    idis
    -0.08
    Į¨
    -0.08
    ç³Ł
    -0.08
    cue
    -0.08
    çĦ¶
    -0.08
    åĬŀ好
    -0.08
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.11
    å§ĭäºİ
    0.11
    æľĢåĪĿ
    0.11
    å¥ijæľº
    0.10
    大æ¦Ĥæĺ¯
    0.10
    æºIJäºİ
    0.10
    orama
    0.09
    æľĢåĪĿçļĦ
    0.09
    ksam
    0.09
    ç¼ĺ
    0.09
    Activations Density 0.114%

    No Known Activations