© 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. 1894
    Prev
    Next
    INDEX
    Explanations

    wacky or funky descriptors

    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
    è¯Ŀ
    -0.11
    sky
    -0.11
    åĬŁåĬ³
    -0.10
    çŀ©
    -0.09
    owing
    -0.09
    ìĦľ
    -0.09
    æŀģ度
    -0.09
    ç¼¥
    -0.09
    holding
    -0.09
    åıijåĬ¨
    -0.09
    POSITIVE LOGITS
    åı¯çĪ±çļĦ
    0.09
    agus
    0.09
    æķĻèĤ²éĥ¨
    0.08
    èĢĮåıĪ
    0.08
    åİŁå§ĭ
    0.08
    è·³è·ĥ
    0.08
     Florence
    0.08
    ä¹Łå°±æĺ¯
    0.08
    uster
    0.08
    eping
    0.08
    Activations Density 0.008%

    No Known Activations