© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29674
    Prev
    Next
    INDEX
    Explanations

    suffix "ance" or "ence"

    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
    Negative Logits
    ter
    -0.15
    the
    -0.15
    ized
    -0.14
    ting
    -0.13
    th
    -0.13
    ization
    -0.13
    åĦ¿
    -0.13
    sh
    -0.13
    trans
    -0.13
    son
    -0.12
    POSITIVE LOGITS
    earch
    0.14
    forth
    0.13
    iros
    0.12
    sing
    0.11
    leep
    0.11
     sake
    0.11
    pire
    0.11
    es
    0.11
    ecurity
    0.10
    inel
    0.10
    Activations Density 0.206%

    No Known Activations