© 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. 26750
    Prev
    Next
    INDEX
    Explanations

    find out

    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
    usc
    -0.10
    æľ¬èº«å°±æĺ¯
    -0.09
    宫
    -0.08
     ÑģоÑģÑĤав
    -0.08
    æľįåĬ¡èĥ½åĬĽ
    -0.08
    çĵĴ
    -0.08
    æĪIJç«ĭäºĨ
    -0.08
     Madagascar
    -0.08
    è´¹çİĩ
    -0.08
    Ñijн
    -0.08
    POSITIVE LOGITS
    asma
    0.10
    èĮµ
    0.10
    庥
    0.09
    ãģĦãģ¾
    0.08
     xuyên
    0.08
    umer
    0.08
    ãģįãģ£ãģ¨
    0.08
    çĽ´è¾¾
    0.08
    fare
    0.08
    halb
    0.08
    Activations Density 0.026%

    No Known Activations