© 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. 3236
    Prev
    Next
    INDEX
    Explanations

    multimedia contents, systems, and services

    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
    OrCreate
    -0.10
    stro
    -0.10
    æµŀ
    -0.09
    æĪĸå°Ĩ
    -0.08
    amientos
    -0.08
    ochond
    -0.08
    ../
    -0.08
    åIJĪéĢĤçļĦ
    -0.08
    èĵį
    -0.08
    à¹Ģà¸ľ
    -0.08
    POSITIVE LOGITS
    åİķ
    0.09
    ATIC
    0.09
    ously
    0.09
    ÑĢеÑĪ
    0.09
    ail
    0.09
    atic
    0.08
    è¸ıä¸Ĭ
    0.08
    ous
    0.08
    æ®ļ
    0.08
    æŀĩ
    0.08
    Activations Density 0.007%

    No Known Activations