© 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. 35027
    Prev
    Next
    INDEX
    Explanations

    from, up, down, across

    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
    æĥ¹
    -0.10
    ãģĮãĤī
    -0.09
    è¶ħé«ĺ
    -0.09
    ãģIJ
    -0.09
     trải
    -0.09
    éªĦåĤ²
    -0.09
    ä¸įæĪIJ
    -0.08
    太太
    -0.08
     бÑĥкв
    -0.08
     اÙĦÙħسؤÙĪÙĦ
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮäºİ
    0.19
    ä¹ĭå¤ĸ
    0.13
     compared
    0.12
     from
    0.12
    äºİ
    0.12
    缸æ¯Ķäºİ
    0.11
    缸æ¯Ķ
    0.11
    缸è¾ĥäºİ
    0.10
    èĦ±ç¦»
    0.10
    èĢĮéĿŀ
    0.10
    Activations Density 0.065%

    No Known Activations