© 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. 32171
    Prev
    Next
    INDEX
    Explanations

    corning leader, xml version, copyright

    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
     Jenner
    -0.08
    æ±Łä¸ľ
    -0.08
    leton
    -0.08
    å®Ļ
    -0.08
    IPP
    -0.08
    NOP
    -0.08
     Perr
    -0.08
    itudes
    -0.08
    æĽ¹æĵį
    -0.08
    ä¿ij
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.10
    æ¼Ĩ
    0.10
    éºŁ
    0.09
    plash
    0.09
    ⾧
    0.09
     dolayı
    0.09
    æ³£
    0.09
     гоÑģÑĥдаÑĢ
    0.08
     má»iji
    0.08
    rase
    0.08
    Activations Density 0.002%

    No Known Activations