© 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. 54326
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns and possessives

    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
    æį®æѤ
    -0.10
    ä»İ严
    -0.09
    oret
    -0.09
    顺çĿĢ
    -0.09
    åİŁåĪĻä¸Ĭ
    -0.09
    ç´¯
    -0.09
    ocene
    -0.09
    å·´æĭī
    -0.09
    ilage
    -0.09
    累计
    -0.09
    POSITIVE LOGITS
    aviest
    0.10
    主é¢ĺ
    0.09
     aspect
    0.09
    æĸ¹éĿ¢
    0.09
     aspects
    0.08
     matter
    0.08
    åħ³åĪĩ
    0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.08
     matters
    0.08
    è¿Ļç¬Ķ
    0.08
    Activations Density 0.225%

    No Known Activations