© 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. 21373
    Prev
    Next
    INDEX
    Explanations

    containers for drinks

    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
    åIJĥ饱
    -0.10
    æĸ¤
    -0.10
    å¸Ľ
    -0.09
    æŀķ
    -0.09
    .ie
    -0.09
    è¿ĻåĿĹ
    -0.08
    好åIJĥ
    -0.08
    çħĮ
    -0.08
    çĬģ
    -0.08
    éĵĨ
    -0.08
    POSITIVE LOGITS
    åĸĿ
    0.16
    æĿ¯
    0.14
    åķľ
    0.14
    饮çĶ¨
    0.13
    æĿ¯åŃIJ
    0.13
    饮åĵģ
    0.12
    åĸĿäºĨ
    0.12
    饮
    0.11
    ä¸Ģåı£
    0.11
     mug
    0.11
    Activations Density 0.076%

    No Known Activations