© 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. 35237
    Prev
    Next
    INDEX
    Explanations

    movement

    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
    å·¥ä½ľæľºåĪ¶
    -0.10
    åIJŀ
    -0.09
    çĶŁæ´»çݯå¢ĥ
    -0.09
    è¿ĩ硬
    -0.09
    为客æĪ·
    -0.09
    ве
    -0.08
    åı¤ä»Ĭ
    -0.08
    åĪĬçĻ»
    -0.08
    åĨł
    -0.08
    åłĤ
    -0.08
    POSITIVE LOGITS
     movement
    0.13
    è¿IJåĬ¨
    0.11
     Movement
    0.11
    æ½®æµģ
    0.11
    ä¸ĢèĤ¡
    0.10
     movements
    0.10
    壮大
    0.10
     движениÑı
    0.10
     rebellion
    0.09
    ä¸Ģæ³¢
    0.09
    Activations Density 0.106%

    No Known Activations