© 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. 62214
    Prev
    Next
    INDEX
    Explanations

    para + Portuguese/Spanish keywords

    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
     behalf
    -0.09
     Ñĩа
    -0.09
    (Parse
    -0.09
    обÑĢаз
    -0.09
    rch
    -0.08
    LESS
    -0.08
    为äºĨ
    -0.08
    ps
    -0.08
    çĪµ
    -0.08
    ials
    -0.08
    POSITIVE LOGITS
    tant
    0.13
    quoi
    0.12
    æľīä¸Ģ天
    0.10
    åĽŀäºĭ
    0.09
    以éĺ²
    0.09
    è¡¥é½IJ
    0.09
    ernals
    0.08
    anean
    0.08
    é¾
    0.08
    anus
    0.08
    Activations Density 0.033%

    No Known Activations