© 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. 1701
    Prev
    Next
    INDEX
    Explanations

    words ending in ion/tion

    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
    å©¿
    -0.12
    ðŁı»
    -0.11
    kes
    -0.11
    ings
    -0.10
    é£İå°ļ
    -0.10
     fashioned
    -0.10
    pper
    -0.10
    uster
    -0.10
    绶
    -0.10
    per
    -0.10
    POSITIVE LOGITS
    naire
    0.26
    aries
    0.18
    naires
    0.18
    nal
    0.17
    nement
    0.16
    ary
    0.16
    aire
    0.16
    ally
    0.16
    aires
    0.15
    ality
    0.15
    Activations Density 0.300%

    No Known Activations