© 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. 27291
    Prev
    Next
    INDEX
    Explanations

    grass or turf

    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
    çĥ¨
    -0.10
    æŃ£å®Ĺ
    -0.09
    UNC
    -0.09
    ì§Ŀ
    -0.09
    ש×Ķ
    -0.09
    æĺ¯ä¸Ģéĥ¨
    -0.09
    -CN
    -0.09
    lesh
    -0.09
    亲åıĭ
    -0.09
    好åıĭ
    -0.09
    POSITIVE LOGITS
    issy
    0.09
    è¦ĨçĽĸçİĩ
    0.08
    ç®
    0.08
    æĪij以为
    0.08
    nier
    0.08
    èĮ«èĮ«
    0.08
    ernen
    0.08
    fair
    0.08
    注åĨĮèµĦæľ¬
    0.08
    engers
    0.07
    Activations Density 0.012%

    No Known Activations