© 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. 35454
    Prev
    Next
    INDEX
    Explanations

    Tron

    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
    æĭ¿åĩº
    -0.09
    æĪij认为
    -0.08
     trem
    -0.08
    å½ĵä¹ĭ
    -0.08
    åĮĸå·¥
    -0.08
    åĨ·åĨ»
    -0.08
    shed
    -0.08
    éľ²
    -0.08
    ARY
    -0.08
    ibu
    -0.08
    POSITIVE LOGITS
    åĩºå·®
    0.09
    åįģåŃĹ
    0.09
    æĸĩ娱
    0.09
    roid
    0.09
    åģıåģı
    0.09
    sterol
    0.09
    bian
    0.09
    读æĩĤ
    0.08
    icial
    0.08
    æ´»å¾Ĺ
    0.08
    Activations Density 0.003%

    No Known Activations