© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8719
    Prev
    Next
    INDEX
    Explanations

    in accordance with

    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
    åŃIJéĩĮ
    -0.09
    ting
    -0.09
    ter
    -0.09
    è¿Ļæł·çļĦè¯Ŀ
    -0.09
    åĦ¿
    -0.09
    åĽłä¸ºåľ¨
    -0.09
    åĴĮåľ°åĮº
    -0.08
    lify
    -0.08
    ensa
    -0.08
    tering
    -0.08
    POSITIVE LOGITS
    гла
    0.09
    åıªå¾Ĺ
    0.09
    upal
    0.09
    bye
    0.09
    sdk
    0.08
    iggs
    0.08
    Çİ
    0.08
    mtree
    0.08
    vertiser
    0.08
    idor
    0.08
    Activations Density 0.020%

    No Known Activations