© 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. 11733
    Prev
    Next
    INDEX
    Explanations

    resistors and wires

    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
    æĶ¶èİ·
    -0.09
    ä¿ĿåŃĺ
    -0.09
    Vo
    -0.08
    æ¹Ľ
    -0.08
    _VO
    -0.08
    æİı
    -0.08
    çªĦ
    -0.08
    ç«ŀéĢī
    -0.08
    OTA
    -0.08
     Clair
    -0.08
    POSITIVE LOGITS
    åĬłçĥŃ
    0.10
    ç¼Ł
    0.10
    åıijçĥŃ
    0.09
    çıŀ
    0.09
    PTY
    0.09
    åĬŁçİĩ
    0.09
     Cro
    0.08
    æĪ¿ä¸ľ
    0.08
    åĩ«
    0.08
     sett
    0.08
    Activations Density 0.061%

    No Known Activations