© 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. 21342
    Prev
    Next
    INDEX
    Explanations

    describing relationship or context

    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
    è¥
    -0.09
    å½¹
    -0.09
    åĮĹ京åĨ¬å¥¥
    -0.09
    pageTitle
    -0.09
    骸
    -0.08
    鸳
    -0.08
    æĿĵ
    -0.08
    强è¡Į
    -0.08
    peg
    -0.08
    quot
    -0.08
    POSITIVE LOGITS
    鸾
    0.10
    èĩ³å°ij
    0.09
    /her
    0.09
     coun
    0.09
    æīĢ以ä»ĸ
    0.09
    æīĭç»Ń
    0.08
    该æĿij
    0.08
    ehr
    0.08
    çļĸ
    0.08
    rab
    0.08
    Activations Density 0.468%

    No Known Activations