© 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. 17510
    Prev
    Next
    INDEX
    Explanations

    I am followed by verb

    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
    访
    -0.09
    éģĹ
    -0.08
    æij¸
    -0.08
    éªģ
    -0.08
    ephy
    -0.08
    éľĨ
    -0.08
     Ñĩа
    -0.08
     bush
    -0.07
    丧失
    -0.07
    æĥłåıĬ
    -0.07
    POSITIVE LOGITS
    åĸĿäºĨ
    0.10
    ãĥIJãĥ©
    0.10
    è§īå¾Ĺå¾Ī
    0.10
    CHANT
    0.10
    缴è¾ĸå¸Ĥ
    0.09
    棺
    0.09
     Ord
    0.09
    ä¹Łæľīå¾Īå¤ļ
    0.09
    ç¦ıå¾·
    0.09
    æ³
    0.09
    Activations Density 0.050%

    No Known Activations