© 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. 33540
    Prev
    Next
    INDEX
    Explanations

    cricket and financial trading

    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
    以为
    -0.09
    æĥĬåı¹
    -0.09
    以çĤº
    -0.09
    殿
    -0.09
    å°±è¡Į
    -0.08
     gating
    -0.08
    çľĭä»ĸ
    -0.08
    è¡Ģ液循çݯ
    -0.08
    çĪµ
    -0.08
    (char
    -0.08
    POSITIVE LOGITS
    åĪ»
    0.09
    ä¼łç»Ł
    0.09
    åĭĸ
    0.09
    ç²¾åĵģ
    0.09
    åºĸ
    0.08
    大æ´ĭ
    0.08
    aded
    0.08
     informant
    0.08
    ä¸ĢåĪ»
    0.08
    æĸĻçIJĨ
    0.08
    Activations Density 0.074%

    No Known Activations