© 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. 23854
    Prev
    Next
    INDEX
    Explanations

    this type of

    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
    åIJĦç§į
    -0.12
    åIJĦèĩªçļĦ
    -0.11
    æĸ°ä¸Ģè½®
    -0.10
    ä¸ĢäºĽ
    -0.10
    èĩªå·±çļĦ
    -0.09
    åĵªäºĽ
    -0.09
    åIJĦç§įåIJĦæł·
    -0.09
    缸åħ³æĶ¿çŃĸ
    -0.09
    åŀĭä¼ģä¸ļ
    -0.09
    ä¸Ģç³»åĪĹ
    -0.08
    POSITIVE LOGITS
    orm
    0.11
    è¿ĩ度
    0.10
    /from
    0.10
     воÑĤ
    0.10
    家ä¼Ļ
    0.09
    etas
    0.09
    ëį°
    0.09
    -sex
    0.09
     warfare
    0.09
    é£ŀè·ĥ
    0.09
    Activations Density 0.051%

    No Known Activations