© 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. 34295
    Prev
    Next
    INDEX
    Explanations

    map layers and styles

    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
    лем
    -0.10
    æīĭæĮĩ
    -0.09
    å°ıèħ¿
    -0.09
    çĵ®
    -0.09
    åĩĨæŶ
    -0.09
    è°¨
    -0.08
    åĪ³
    -0.08
     completeness
    -0.08
    æħİ
    -0.08
    硬åĮĸ
    -0.08
    POSITIVE LOGITS
    zik
    0.09
    çĻ¾å®¶
    0.09
    æļ®
    0.09
    ç²¾èĭ±
    0.08
    éĥ½è®¤ä¸º
    0.08
    ѣ
    0.08
    æĿ¥èĩª
    0.08
    åĽĽåŃ£
    0.08
    çģµæĦŁ
    0.08
    æľĢä½³
    0.08
    Activations Density 0.128%

    No Known Activations