© 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. 34819
    Prev
    Next
    INDEX
    Explanations

    -ation, -ition, -uction suffixes

    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
    ings
    -0.16
    åĦ¿
    -0.15
    ÂŃing
    -0.12
    ural
    -0.11
    ify
    -0.11
    ingly
    -0.11
    ación
    -0.10
    aceut
    -0.10
    è¿Ļæł·çļĦè¯Ŀ
    -0.10
    est
    -0.10
    POSITIVE LOGITS
    ary
    0.19
    ми
    0.15
    naire
    0.15
    nist
    0.14
    ally
    0.13
    nal
    0.13
    nelle
    0.12
    nel
    0.12
    ist
    0.11
    æѤåĪ»
    0.10
    Activations Density 2.067%

    No Known Activations