© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8594
    Prev
    Next
    INDEX
    Explanations

    scientific reporting and findings

    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
    >Main
    -0.08
    åĬĤ
    -0.08
    çݯå¢ĥä¸ĭ
    -0.08
    æİĸ
    -0.08
    åĺ´åĶĩ
    -0.08
    ofs
    -0.08
    åĮºéĹ´
    -0.07
     Patron
    -0.07
     patron
    -0.07
    á¼Ī
    -0.07
    POSITIVE LOGITS
    éĿ¶
    0.11
    æĬĺåıł
    0.09
    Investigators
    0.08
    æĭĽåĭŁ
    0.08
    åĪĨåŃIJ
    0.07
    ç͍ç͵
    0.07
     repro
    0.07
    è¡Į使
    0.07
    воÑĢоÑĤ
    0.07
    以èī²
    0.07
    Activations Density 3.956%

    No Known Activations