© 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. 63731
    Prev
    Next
    INDEX
    Explanations

    also known as

    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
    çĤķ
    -0.11
    æ£ĭ
    -0.10
    anton
    -0.10
    ä»Ģ
    -0.09
    ç»ıéªĮ丰å¯Į
    -0.09
    tsy
    -0.09
     apl
    -0.09
    éºĴ
    -0.09
    ford
    -0.08
    ibal
    -0.08
    POSITIVE LOGITS
    åı«åģļ
    0.13
    åıĪ称
    0.12
    称为
    0.12
    稱
    0.11
     called
    0.11
    称
    0.10
    à¹ģà¸Ļ
    0.10
    called
    0.10
    also
    0.09
    åı«
    0.09
    Activations Density 0.118%

    No Known Activations