© 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. 58033
    Prev
    Next
    INDEX
    Explanations

    marker, turnover, cgi, fer, idl

    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¸įèĥ½åĨį
    -0.11
    çļĦçľ¼
    -0.10
    æīįç®Ĺ
    -0.09
    åĨľæĪ·
    -0.09
    æ½ľ
    -0.09
    çĶ©
    -0.09
    ä¸įæĺİçĻ½
    -0.08
     Repository
    -0.08
    æ³¾
    -0.08
    ãĢĿ
    -0.08
    POSITIVE LOGITS
    ä¿¡å¿ĥ
    0.11
    idl
    0.10
    èIJ©
    0.10
     cgi
    0.09
     Kang
    0.08
    ç²ĺ
    0.08
    çŀ½
    0.08
     fer
    0.08
    çĮĸ
    0.08
    eger
    0.08
    Activations Density 0.080%

    No Known Activations