© 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. 18195
    Prev
    Next
    INDEX
    Explanations

    chief executive officer titles

    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
    ä¸įè¦ģ太
    -0.09
    ç»Ħå§Ķä¼ļ
    -0.08
    asio
    -0.08
    å¾Īæľī
    -0.08
    isy
    -0.08
     very
    -0.08
    æĪIJåĪĨ
    -0.08
     Very
    -0.08
    aise
    -0.08
    iras
    -0.07
    POSITIVE LOGITS
    æĥķ
    0.11
    åłĩ
    0.11
    еÑħ
    0.10
    è¶Ł
    0.10
    æļ¾
    0.09
     Pars
    0.09
    ç»ĥ
    0.09
    èĪ¸
    0.09
    åĪ¹
    0.09
    eten
    0.09
    Activations Density 0.049%

    No Known Activations