© 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. 8872
    Prev
    Next
    INDEX
    Explanations

    movement and control within environments

    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
    å¼ĥ
    -0.10
    æ£Ħ
    -0.10
    ä¸įå°½
    -0.10
    åħ¼èģĮ
    -0.09
    åĽ½æĥħ
    -0.09
     naked
    -0.09
    åħ»
    -0.09
    æĹłåı¯
    -0.09
    ording
    -0.09
    pone
    -0.09
    POSITIVE LOGITS
    ä¸Ģåıªæīĭ
    0.10
    çģ¯
    0.09
    ADER
    0.09
     Wheel
    0.09
    æĦŁè§īèĩªå·±
    0.09
    èĬ¸
    0.08
    ç²ĺ
    0.08
     Pill
    0.08
    GRAM
    0.08
    æģ¯
    0.08
    Activations Density 0.053%

    No Known Activations