© 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. 30598
    Prev
    Next
    INDEX
    Explanations

    All rights reserved

    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
    nej
    -0.10
    ëĶ°
    -0.10
    isl
    -0.09
    /licenses
    -0.09
    QUIT
    -0.09
    è´¹çİĩ
    -0.09
    ÙĬس
    -0.09
    æµļ
    -0.08
    ARP
    -0.08
    æľŁåĨħ
    -0.08
    POSITIVE LOGITS
    åıijæĮ¥äºĨ
    0.08
    osal
    0.08
    çķª
    0.08
    åı¦ä¸Ģè¾¹
    0.08
    红æĺŁ
    0.08
    çŃĸ
    0.08
    anova
    0.08
    å«ĸ
    0.08
    ¡°
    0.08
    åı£ç¢ij
    0.08
    Activations Density 0.033%

    No Known Activations