© 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. 20025
    Prev
    Next
    INDEX
    Explanations

    these followed by nouns

    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
    sWith
    -0.12
    esc
    -0.11
    sons
    -0.10
     itself
    -0.10
    son
    -0.10
    ness
    -0.09
    æĢ§å¼º
    -0.09
    swith
    -0.09
    è¿Ļ家
    -0.09
    éĤ£ç§į
    -0.09
    POSITIVE LOGITS
    å¹´æĿ¥
    0.18
    quence
    0.16
     beiden
    0.13
     же
    0.12
    cond
    0.11
    家ä¼Ļ
    0.11
    lection
    0.11
     sorts
    0.11
    venth
    0.11
    ason
    0.11
    Activations Density 0.086%

    No Known Activations