© 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. 61703
    Prev
    Next
    INDEX
    Explanations

    possessives and contractions

    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
    åĦ¿
    -0.12
    er
    -0.09
    s
    -0.09
    æĸ¼æĺ¯
    -0.08
    i
    -0.08
    ero
    -0.08
    ei
    -0.08
    è¿ĻåĦ¿
    -0.08
     persuasion
    -0.08
    å°±è¿Ļæł·
    -0.07
    POSITIVE LOGITS
    èĩ¾
    0.10
    eneg
    0.10
    owed
    0.10
    çħ
    0.10
    زاÙĦ
    0.10
    eworthy
    0.09
    boro
    0.09
    ç»ıéªĮåĴĮ
    0.09
    ouro
    0.09
    éĤķ
    0.09
    Activations Density 0.048%

    No Known Activations