© 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. 1290
    Prev
    Next
    INDEX
    Explanations

    who you are becoming

    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
    çī¢
    -0.10
    åIJĦèĩªçļĦ
    -0.09
    èģĮè´£
    -0.09
    çī¢åĽº
    -0.09
    éķ¿å¯¿
    -0.09
    ittal
    -0.09
    è¾Ľ
    -0.08
    çĪ¬
    -0.08
    kes
    -0.08
    æĺĩ
    -0.08
    POSITIVE LOGITS
    赤
    0.10
    åIJĦæĸ¹éĿ¢
    0.09
    tier
    0.09
    ç¼ģ
    0.09
    ä¸įåı¯æĪĸ缺
    0.09
    ä¸įåı¯ç¼ºå°ij
    0.09
    åĩºåİĤ
    0.09
    岸
    0.09
     congr
    0.09
    ticks
    0.09
    Activations Density 0.040%

    No Known Activations