© 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. 27194
    Prev
    Next
    INDEX
    Explanations

    He later, he was, his calm

    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
    èĤļ
    -0.09
    èݹ
    -0.08
    çıł
    -0.08
    å½±
    -0.08
    iol
    -0.08
    åŃ£
    -0.08
    gw
    -0.08
    èĬŁ
    -0.08
    éĵ¢
    -0.08
    æĺİçıł
    -0.08
    POSITIVE LOGITS
    çķĻåѦçĶŁ
    0.10
    è¶ħé¢Ŀ
    0.10
    åĪĽéĢłæĢ§
    0.09
    å±¥èģĮ
    0.09
    quot
    0.09
    æīĢå±ŀ
    0.09
    主åĬĽ
    0.09
    伤亡
    0.09
    骨干
    0.08
    ä¸İä¼Ĺ
    0.08
    Activations Density 0.139%

    No Known Activations