© 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. 10084
    Prev
    Next
    INDEX
    Explanations

    dining experience

    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
    ×ķת
    -0.10
    teen
    -0.09
    çłĶ究ä¸Ńå¿ĥ
    -0.09
    ariat
    -0.09
    mente
    -0.09
    ions
    -0.08
    dre
    -0.08
    åĩıè½»
    -0.08
    ή
    -0.08
    个å¤ļ
    -0.08
    POSITIVE LOGITS
    osaurs
    0.10
    -away
    0.10
    室
    0.10
    æ¦Ķ
    0.09
    engl
    0.09
    ìĦĿ
    0.09
    felt
    0.09
    æ¡Įä¸Ĭ
    0.09
    tain
    0.09
    noc
    0.09
    Activations Density 0.006%

    No Known Activations