© 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. 18656
    Prev
    Next
    INDEX
    Explanations

    granted, violated, rights, difficult

    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
    æıŃ示
    -0.09
    çļĦæĦŁæĥħ
    -0.09
    æīĢåľ¨çļĦ
    -0.09
    /graphql
    -0.09
    æĭľ
    -0.08
    éű
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    é£İè²Į
    -0.08
    ORLD
    -0.08
    лем
    -0.08
    POSITIVE LOGITS
    è¡Į使
    0.11
    享
    0.10
    à¸ķà¸ģ
    0.10
    ä¿ĿæĬ¤
    0.10
     enjoyed
    0.09
    åŀĤ
    0.09
    ä¿ĿèŃ·
    0.09
     freedom
    0.09
    ä¿Ŀéļľ
    0.09
    ivr
    0.08
    Activations Density 0.238%

    No Known Activations