© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52152
    Prev
    Next
    INDEX
    Explanations

    already joined or missed problems

    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
    éĿŀ常å¤ļ
    -0.09
    nable
    -0.09
    oga
    -0.09
     Lent
    -0.08
    (Program
    -0.08
    otle
    -0.08
     ÑģобÑģÑĤвенно
    -0.08
    frog
    -0.08
    cery
    -0.08
    _dur
    -0.07
    POSITIVE LOGITS
    äºĨåIJĹ
    0.16
    åIJĹ
    0.14
    åĹİ
    0.13
    ãģ§ãģĻãģĭ
    0.12
    çļĦè¯Ŀ
    0.12
    ç´¯äºĨ
    0.12
    Õŀ
    0.11
    çļĦ人éĥ½
    0.11
    ï¼Ł
    0.11
    å°ijäºĨ
    0.10
    Activations Density 0.115%

    No Known Activations