© 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. 8519
    Prev
    Next
    INDEX
    Explanations

    racing related terms

    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
    ary
    -0.10
    itary
    -0.09
    ives
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    aries
    -0.09
    OrCreate
    -0.08
    ori
    -0.08
    holding
    -0.08
     Rif
    -0.08
    âľĸ
    -0.08
    POSITIVE LOGITS
    ound
    0.10
    dio
    0.10
    ä¸įçĦ¶
    0.10
    /OR
    0.09
    ×ķ×ļ
    0.09
    anten
    0.09
    æݨåĩºäºĨ
    0.09
    ðŁĴ¨
    0.09
    ħ
    0.08
    ands
    0.08
    Activations Density 0.010%

    No Known Activations