© 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. 17573
    Prev
    Next
    INDEX
    Explanations

    places and regions

    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
    tif
    -0.09
    ä¼ŀ
    -0.08
    åĽ½æĹĹ
    -0.08
    uario
    -0.08
    ç¦ıåĪ©
    -0.08
    åĪºå®¢
    -0.08
    uent
    -0.08
     President
    -0.08
    istar
    -0.08
    çĪ±å¿ĥ
    -0.08
    POSITIVE LOGITS
    è¡·
    0.10
    ä¸Ģ对ä¸Ģ
    0.09
    çĶļ
    0.09
    åį³ä½¿
    0.09
    ement
    0.09
     Excell
    0.08
    [#
    0.08
    ترا
    0.08
    arend
    0.08
    å±ij
    0.08
    Activations Density 0.004%

    No Known Activations