© 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. 18288
    Prev
    Next
    INDEX
    Explanations

    more information

    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
     оÑĩеÑĢед
    -0.10
    èĢģ头
    -0.10
    inned
    -0.10
    ç¢į
    -0.09
    ippi
    -0.09
    主æĦı
    -0.09
    è¡Įè´¿
    -0.09
    æŦ
    -0.09
     ÑģоÑģÑĤ
    -0.09
    èĩĤ
    -0.09
    POSITIVE LOGITS
    æĮĤåı·
    0.08
    esc
    0.08
    è·ij
    0.07
    èµ·æĿ¥äºĨ
    0.07
    æĸĹ
    0.07
    edom
    0.07
    èĩ³å°Ĭ
    0.07
     CIS
    0.07
    æ¯į
    0.07
    çijķ
    0.07
    Activations Density 0.014%

    No Known Activations