© 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. 53206
    Prev
    Next
    INDEX
    Explanations

    public meetings and announcements

    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
    èĨº
    -0.09
    isas
    -0.09
    æ±ĩ
    -0.09
    äºİä¸Ģä½ĵ
    -0.08
    æĤ¨åIJĮæĦı
    -0.08
    ä»°
    -0.08
    ìĭ
    -0.08
     moder
    -0.08
    æģ°
    -0.08
     Trusted
    -0.08
    POSITIVE LOGITS
    åħ¬ä¼Ĺ
    0.11
    èĤ¢
    0.11
    adin
    0.10
    æĹłå£°
    0.10
    åħ¬ç¤º
    0.10
     зÑĢ
    0.10
    åĮ¿åIJį
    0.09
    æĿijæ°ij
    0.09
    åħ¬å¼Ģ
    0.09
    ä¿¡æģ¯åħ¬å¼Ģ
    0.09
    Activations Density 0.041%

    No Known Activations