© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37688
    Prev
    Next
    INDEX
    Explanations

    activist organizations and advocacy groups

    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
    relude
    -0.09
    ittel
    -0.09
    SSIP
    -0.09
     Jeb
    -0.09
    æļĩ
    -0.09
    ç¨Ĺ
    -0.08
    丧
    -0.08
     currentState
    -0.08
    æĦİ
    -0.08
    íĥĿ
    -0.08
    POSITIVE LOGITS
    ãĥ¼ãĤº
    0.08
    æIJģ
    0.08
    å¹²åĩĢ
    0.08
    åĴĮ个人
    0.08
     TSR
    0.08
    ç»´æĿĥ
    0.08
    ç¼ļ
    0.08
    èĦ¾æ°Ķ
    0.08
    iciel
    0.08
    .ArrayAdapter
    0.08
    Activations Density 0.122%

    No Known Activations