© 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. 35376
    Prev
    Next
    INDEX
    Explanations

    making kitchen items from old materials

    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
    åĴĮå®ĮåĸĦ
    -0.11
    åħ¨åĽ½äººæ°ij
    -0.11
    约ä¼ļ
    -0.11
    ç»ĦåĽ¾
    -0.10
    æī§æĶ¿
    -0.10
    æ¯Ķäºļ
    -0.09
    活泼
    -0.09
    åį®
    -0.09
    è¿ĻæĶ¯
    -0.09
    ç³»
    -0.09
    POSITIVE LOGITS
    ç¾İæľ¯
    0.09
    Originally
    0.09
     originally
    0.09
    åİŁæľīçļĦ
    0.09
     unused
    0.09
    çĶ¨æĿ¥
    0.09
    没人
    0.08
     leftover
    0.08
     discarded
    0.08
    åºŁå¼ĥ
    0.08
    Activations Density 0.145%

    No Known Activations