© 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. 33778
    Prev
    Next
    INDEX
    Explanations

    number of

    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
    åĺı
    -0.10
    apter
    -0.09
    amate
    -0.09
    Õ¬
    -0.09
    æĭ¦
    -0.09
    atsu
    -0.09
    è¿Ļç§įæĸ¹æ³ķ
    -0.09
    abb
    -0.09
    çıŀ
    -0.09
    è¾½å®ģ
    -0.09
    POSITIVE LOGITS
     Leh
    0.09
    .respond
    0.08
    人æŃ»äº¡
    0.08
    ograph
    0.08
    声åĵį
    0.08
    .getTag
    0.07
    究
    0.07
    ÙĪار
    0.07
    天空
    0.07
    æĥij
    0.07
    Activations Density 0.332%

    No Known Activations