© 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. 50561
    Prev
    Next
    INDEX
    Explanations

    spiritual restoration and physical needs

    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
    èĩªæķij
    -0.10
    åī¥å¤º
    -0.10
    ç¾Ķ
    -0.09
    åıĺäºĨ
    -0.09
    åIJ¬çĿĢ
    -0.09
     accommod
    -0.09
    룸
    -0.09
    /manual
    -0.08
    lap
    -0.08
    è¹ļ
    -0.08
    POSITIVE LOGITS
    顺åĪ©
    0.11
    åĪĽä¸ļ
    0.10
    èĩ£
    0.09
    åѦä¸ļ
    0.09
    好è¿IJ
    0.09
     Ars
    0.09
    éĤª
    0.09
    ä»ķ
    0.09
    desired
    0.09
    äºĭä¸ļ
    0.08
    Activations Density 0.046%

    No Known Activations