© 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. 21554
    Prev
    Next
    INDEX
    Explanations

    tax and financial terms

    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
     Sharp
    -0.09
    åħĪéĶĭ
    -0.08
    çĿ£ä¿ĥ
    -0.08
    éĻĪåĪĹ
    -0.08
    em
    -0.08
    1
    -0.08
     mir
    -0.08
    èIJĥ
    -0.08
    éĶIJ
    -0.08
    è®®
    -0.08
    POSITIVE LOGITS
    ç´§å¯Ĩç»ĵåIJĪ
    0.10
    æķ¬ä¸ļ
    0.10
    ä¸IJ
    0.10
    åIJĿ
    0.10
    ваÑĢ
    0.10
    æĥ
    0.10
    antaged
    0.09
    éªĪ
    0.09
    顾
    0.09
    èī¯å¿ĥ
    0.09
    Activations Density 0.037%

    No Known Activations