© 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. 19694
    Prev
    Next
    INDEX
    Explanations

    streets, avenues, thoroughfares

    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
    åĴ¬
    -0.11
    æĪijçľģ
    -0.10
    客æĪ·æıIJä¾Ľ
    -0.09
    èıŁ
    -0.09
    åħ¨ç¤¾ä¼ļ
    -0.09
    æĻ¦
    -0.09
    äºŃ
    -0.09
    åºĦåĽŃ
    -0.09
    azi
    -0.09
    è¿«
    -0.08
    POSITIVE LOGITS
    大è¡Ĺ
    0.12
    æŃ¥è¡Į
    0.11
    è¿ĻæĿ¡
    0.11
    èģļéĽĨ
    0.11
     street
    0.11
    street
    0.11
    è¡ĹåĮº
    0.11
    è¡Ĺéģĵ
    0.10
    沿çĿĢ
    0.10
    人æµģ
    0.10
    Activations Density 0.079%

    No Known Activations