© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8905
    Prev
    Next
    INDEX
    Explanations

    articles describing common prepositions

    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
    éķ¿å¤§
    -0.10
    æĬĦ
    -0.10
    çIJħ
    -0.09
    座
    -0.09
    第ä¸ĢçĻ¾
    -0.09
    åıĪæĺ¯
    -0.08
    ogl
    -0.08
    æĺ¨
    -0.08
    æĪIJåŀĭ
    -0.08
    era
    -0.08
    POSITIVE LOGITS
    桧
    0.10
    vang
    0.09
    绫
    0.09
    AAP
    0.09
    arty
    0.09
    uida
    0.09
    rup
    0.09
    åĩ¯
    0.09
    è°ĭ
    0.09
     Ñģебе
    0.09
    Activations Density 0.795%

    No Known Activations