© 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. 26652
    Prev
    Next
    INDEX
    Explanations

    meat cuts and body parts

    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
    è¡£æŁľ
    -0.10
    åIJĮä»ģ
    -0.10
    é³³
    -0.09
    çłģ头
    -0.09
    éŨåīį
    -0.09
    èij«èĬ¦
    -0.09
    fixture
    -0.09
    çĦļçĥ§
    -0.08
    é»Ħçĵľ
    -0.08
    èĢĮæĺ¯
    -0.08
    POSITIVE LOGITS
    è¡«
    0.09
    ONA
    0.08
    erta
    0.08
    åľ¨å¹¿å·ŀ
    0.08
    IFIC
    0.08
    æľīå¿ħè¦ģ
    0.08
    &utm
    0.08
     roast
    0.08
    èİŀ
    0.08
    ners
    0.08
    Activations Density 0.009%

    No Known Activations