© 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. 31496
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ERY
    -0.11
     Yao
    -0.11
    ery
    -0.10
    çĤ¹å¤ļ
    -0.09
    ä¸ĢèĦļ
    -0.09
    æİ£
    -0.09
    å±ŀäºİèĩªå·±
    -0.09
    åIJĨ
    -0.09
    ä»Ģä¹ĪåİŁåĽł
    -0.08
    yard
    -0.08
    POSITIVE LOGITS
    hana
    0.08
    æŁĿ
    0.08
    æįIJ
    0.08
    AGER
    0.08
    umbles
    0.08
    ç¬ı
    0.08
    çģ«çĤ¬
    0.08
    apr
    0.08
    nf
    0.08
    .createClass
    0.08
    Activations Density 0.000%

    No Known Activations