© 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. 58759
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and generations

    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
    éį
    -0.10
    çĥĽ
    -0.09
    ç«Ł
    -0.09
    ì°©
    -0.09
    çİĦ
    -0.09
    åIJĪéĢĤçļĦ
    -0.09
    dish
    -0.09
    è§Ħ磩
    -0.08
    人æŃ»äº¡
    -0.08
     Dw
    -0.08
    POSITIVE LOGITS
    æĹ¶ä»£
    0.12
    第ä¸ī代
    0.12
    æĹ¶ä»£çļĦ
    0.10
    PTY
    0.09
     parad
    0.09
    第ä¸ī次
    0.09
    æĸ°æĹ¶ä»£
    0.09
    ä¸Ģ代
    0.09
    æĻĤ代
    0.09
    第äºĮ
    0.09
    Activations Density 0.099%

    No Known Activations