© 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. 4706
    Prev
    Next
    INDEX
    Explanations

    future, time, and dates

    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
    壮
    -0.10
    壯
    -0.09
    åıł
    -0.08
    çľĩ
    -0.08
    oir
    -0.08
    康
    -0.08
    äºĶæľĪ
    -0.08
    (ro
    -0.08
    REM
    -0.08
    aty
    -0.08
    POSITIVE LOGITS
    æĭĨ
    0.10
    icina
    0.10
    éĥ½ä¸įèĥ½
    0.10
    ä¹ĭæĥħ
    0.09
    maal
    0.09
    istar
    0.09
     hakkında
    0.09
    ãĥ¼ãĤ¹
    0.09
     toll
    0.08
    åľ¨æ¸¸æĪıä¸Ń
    0.08
    Activations Density 0.281%

    No Known Activations