© 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. 18321
    Prev
    Next
    INDEX
    Explanations

    in `the` after `are`

    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
     ÐľÐ¾Ñģ
    -0.11
     новоÑģÑĤи
    -0.10
    ä¸Ńå¿ĥ主任
    -0.10
    翦
    -0.10
    âĸ¾
    -0.10
    abby
    -0.10
    -lnd
    -0.10
    éĻ¢éĻ¢éķ¿
    -0.10
    IES
    -0.09
    çŃ²
    -0.09
    POSITIVE LOGITS
    å·§
    0.09
    S
    0.08
     "
    0.08
    æ³½
    0.08
    ris
    0.08
    lest
    0.08
    s
    0.07
    é¥ŃåºĹ
    0.07
    ought
    0.07
     st
    0.07
    Activations Density 0.085%

    No Known Activations