© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9101
    Prev
    Next
    INDEX
    Explanations

    movement, motion, actuators

    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
    iline
    -0.10
    åİŁå§ĭ
    -0.09
    åŃĹåı·
    -0.09
    åĨ³
    -0.09
    æĶ¸
    -0.09
    .activation
    -0.09
    ç¾Ĭ
    -0.09
    åIJĥäºı
    -0.09
    à¤ĺ
    -0.09
    çļĦç«ŀäºī
    -0.08
    POSITIVE LOGITS
    追éļı
    0.10
    追
    0.10
    æŃ¥ä¼IJ
    0.10
     каÑĩ
    0.10
    æĬĸ
    0.09
    å·į
    0.09
    çĻ½èī²
    0.09
     movement
    0.09
     motion
    0.08
    æĦŁæĥħ
    0.08
    Activations Density 0.239%

    No Known Activations