© 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. 61349
    Prev
    Next
    INDEX
    Explanations

    years and older / or older

    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
    ä¸ºæľŁ
    -0.10
    äºĶåħŃ
    -0.10
    ä¸īåĽĽ
    -0.10
    æĺŁåº§
    -0.10
    èį©
    -0.10
    åħ³å¿ĥ
    -0.09
    ä¸ĢäºĮ
    -0.09
    æľĪä¸Ń
    -0.09
    æ¹ĸåĮº
    -0.09
    åįĬ个
    -0.09
    POSITIVE LOGITS
    ç¾ŀ
    0.08
    *
    0.08
    å¤ļäºĨ
    0.08
    ä¹ĭä¸ĭ
    0.08
    pike
    0.08
    avern
    0.08
    artin
    0.08
    çĽ¸ä¼ł
    0.07
    以ä¸Ĭ
    0.07
    æ±ī
    0.07
    Activations Density 0.016%

    No Known Activations