© 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. 55242
    Prev
    Next
    INDEX
    Explanations

    and followed by

    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
    ТЬ
    -0.09
    ÑģÑģ
    -0.09
    uther
    -0.09
    çIJ¥
    -0.09
    çļĦåĬĽéĩı
    -0.09
    çļĦçľ¼åħī
    -0.08
    驾
    -0.08
    оÑĢо
    -0.08
    RadioButton
    -0.08
    adro
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.10
    èĪ¬çļĦ
    0.10
    inding
    0.09
    éĻĽ
    0.08
    iest
    0.08
    è¾Ħ
    0.08
    æķĪåºĶ
    0.08
    ElementsBy
    0.08
     Kon
    0.08
    æĿµ
    0.08
    Activations Density 0.369%

    No Known Activations