© 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. 63242
    Prev
    Next
    INDEX
    Explanations

    latin 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
    аÑĤелÑĮ
    -0.08
    ed
    -0.08
    asant
    -0.08
    orable
    -0.08
    antas
    -0.08
    /vendors
    -0.08
    antasy
    -0.07
    ÅĤa
    -0.07
    rog
    -0.07
    ates
    -0.07
    POSITIVE LOGITS
    ि
    0.16
    ium
    0.16
    ãģĦãģ§
    0.15
    ãģĦ
    0.15
    ian
    0.15
    ิ
    0.14
    ÙĬØ©
    0.14
    ius
    0.14
    ии
    0.14
    Ùī
    0.14
    Activations Density 0.910%

    No Known Activations