© 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. 6549
    Prev
    Next
    INDEX
    Explanations

    animal groups

    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
    ä¼ĺ
    -0.10
    å®ĺ
    -0.09
    赧
    -0.09
    ophon
    -0.09
    磮
    -0.08
    éģį
    -0.08
    ä¸Ģ个å¤ļ
    -0.08
     Trom
    -0.08
    çĶľçĶľ
    -0.08
    fers
    -0.08
    POSITIVE LOGITS
    çī¡
    0.10
    æİĢ
    0.10
     dục
    0.09
    ä¸ŃåĽ½åĪ¶éĢł
    0.09
    主任
    0.09
    ä¸Ģ群
    0.09
    icle
    0.09
    posable
    0.09
    çıŃåŃIJ
    0.09
    åĢ¾
    0.09
    Activations Density 0.088%

    No Known Activations