© 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. 61785
    Prev
    Next
    INDEX
    Explanations

    automatically, naturally, happens

    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
    è´»
    -0.10
    缼åħ¸
    -0.09
    以èī²
    -0.09
    å®´ä¼ļ
    -0.09
    ä¸ĵéŨ
    -0.09
    ç¿ķ
    -0.08
    ãģ«æĪ
    -0.08
    åIJĥè¿ĩ
    -0.08
    æķijåij½
    -0.08
    峪
    -0.08
    POSITIVE LOGITS
    èĩªçĦ¶èĢĮçĦ¶
    0.24
    èĩªçĦ¶èĢĮ
    0.19
    èĩªçĦ¶
    0.17
     naturally
    0.15
    ä¸įçŁ¥ä¸įè§ī
    0.13
    被åĬ¨
    0.13
    èĩªåıij
    0.13
    èĩªåĬ¨
    0.13
     ìŀIJìĹ°
    0.13
     Automatically
    0.12
    Activations Density 0.072%

    No Known Activations