© 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. 11094
    Prev
    Next
    INDEX
    Explanations

    sustainable development goals

    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
    chn
    -0.12
    éĿ¢çĻ½
    -0.10
    éĦĤ
    -0.09
    éªijè¡Į
    -0.09
    è¿Ļä¹Ī说
    -0.09
    å¹³æŶ
    -0.09
    å½±åĵįåĬĽ
    -0.09
    对å¤ĸ
    -0.09
     Neck
    -0.09
    éħ¹
    -0.09
    POSITIVE LOGITS
    缮æłĩ
    0.11
    缮æ¨Ļ
    0.10
     jq
    0.09
    第ä¸ĢæĿ¡
    0.09
    纲
    0.09
     targets
    0.09
     objectives
    0.09
     goals
    0.09
    çļĦ缮æłĩ
    0.08
     Targets
    0.08
    Activations Density 0.046%

    No Known Activations