© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9668
    Prev
    Next
    INDEX
    Explanations

    anti-drug treatments

    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
    管çIJĨä¸Ńå¿ĥ
    -0.12
    éľīç´ł
    -0.09
    è´Łè´£äºº
    -0.09
    åīįä¸įä¹ħ
    -0.09
    ÑģÑĤи
    -0.09
    稳
    -0.09
    ieg
    -0.09
    å¤ļåĬŁèĥ½
    -0.09
    bane
    -0.09
    æĢİä¹ĪåĽŀäºĭ
    -0.09
    POSITIVE LOGITS
    æݪæĸ½
    0.12
    åīĤ
    0.12
    OTE
    0.09
    åĸ·
    0.08
    ми
    0.08
    atives
    0.08
    orderby
    0.08
     Bahrain
    0.08
    ãĥIJãĥª
    0.08
    ening
    0.08
    Activations Density 0.212%

    No Known Activations