© 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. 27175
    Prev
    Next
    INDEX
    Explanations

    image and its context

    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
    äººæł¼
    -0.08
    æ²½
    -0.08
    uting
    -0.08
    åĵģåij³
    -0.08
    yes
    -0.08
    ×ŀס
    -0.08
    è°ĥåij³
    -0.07
    款
    -0.07
    äºĨä¸Ģåľº
    -0.07
    ç²¾ç¥ŀæĸĩæĺİ
    -0.07
    POSITIVE LOGITS
    çĪ
    0.12
    .setImageResource
    0.10
    .IMAGE
    0.10
    :image
    0.09
    /svg
    0.09
    çĥĤ
    0.09
    .image
    0.09
    ç»ıåħ¸çļĦ
    0.09
    /image
    0.09
    .Images
    0.08
    Activations Density 0.019%

    No Known Activations