© 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. 54624
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¸ĢåĢĭ人
    -0.10
    ä¸Ģ个人
    -0.10
    üss
    -0.10
    posables
    -0.10
    AVE
    -0.10
    ache
    -0.09
    iegel
    -0.09
    áĥ£
    -0.09
    åľ¨æ¸¸æĪıä¸Ń
    -0.09
    mate
    -0.08
    POSITIVE LOGITS
    eq
    0.08
     Rolls
    0.08
    ailed
    0.08
    èĤĨ
    0.08
    åıijåĩº
    0.08
    ä¸ĸ人
    0.08
    ило
    0.08
     Madness
    0.08
    .config
    0.08
    èħ¿
    0.08
    Activations Density 0.000%

    No Known Activations