© 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. 57691
    Prev
    Next
    INDEX
    Explanations

    income, technology, cooking, illness

    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
    sher
    -0.11
    æµİ
    -0.11
    [*
    -0.09
    uses
    -0.09
    sic
    -0.08
    æľĢéĩįè¦ģçļĦ
    -0.08
    uche
    -0.08
    认为
    -0.08
    usk
    -0.08
    ä¸įæŃ¢
    -0.07
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.15
    æľ¬èº«çļĦ
    0.13
    æľ¬èº«
    0.13
     ÑģобÑģÑĤвенно
    0.12
     necessarily
    0.10
    èĩªèº«çļĦ
    0.09
    æĿĢ人
    0.09
    æŦ
    0.09
    綦
    0.09
    çļĦéĹ®é¢ĺ
    0.09
    Activations Density 0.099%

    No Known Activations