© 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. 53994
    Prev
    Next
    INDEX
    Explanations

    legal document footers

    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
    ally
    -0.09
    ors
    -0.09
    favicon
    -0.09
    yses
    -0.08
    âĨµ
    -0.08
    è¿Ļæīį
    -0.08
    å·¢
    -0.08
    å²
    -0.08
    ä¼ĺå¼Ĥ
    -0.08
    ocket
    -0.08
    POSITIVE LOGITS
    绿水
    0.09
    unist
    0.09
    èļĤ
    0.09
    ç»°
    0.09
    ä¸Ģ声
    0.09
    NewLabel
    0.09
    baar
    0.09
    寰
    0.09
    æīĵäºĨ
    0.08
    ination
    0.08
    Activations Density 0.112%

    No Known Activations