© 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. 2514
    Prev
    Next
    INDEX
    Explanations

    make a difference

    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
    erge
    -0.10
    é£İæ³¢
    -0.09
    lings
    -0.09
    æ»´æ»´
    -0.09
    äºŃ
    -0.09
    许å¤ļ人
    -0.08
    .pa
    -0.08
    éĶ¢
    -0.08
    èĭĽ
    -0.08
     cgi
    -0.08
    POSITIVE LOGITS
    ãĤĬ
    0.10
    affer
    0.09
    дав
    0.09
    веден
    0.09
    stroy
    0.09
    æ°ijçĶŁ
    0.09
    æĹ¥å¸¸çĶŁæ´»
    0.09
    alist
    0.08
    вед
    0.08
    iber
    0.08
    Activations Density 0.004%

    No Known Activations