© 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. 30176
    Prev
    Next
    INDEX
    Explanations

    two followed by plural nouns

    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
    äºĨä¸įå°ij
    -0.10
    AT
    -0.08
    åĪĨ红
    -0.08
    äºĨ许å¤ļ
    -0.08
    æľī人说
    -0.08
    è¿Ļæīį
    -0.08
    ãĤ«ãĥ¼
    -0.08
     пÑĥ
    -0.08
    ow
    -0.08
    åıĭ们
    -0.08
    POSITIVE LOGITS
    abbo
    0.11
    以åıĬåħ¶ä»ĸ
    0.10
    ucch
    0.10
    çĨŁæĤīçļĦ
    0.10
    èł²
    0.09
     alone
    0.09
    æ¾Ħ
    0.09
    æ»Ķ
    0.09
    èĢĮå·²
    0.09
    æĸ
    0.08
    Activations Density 0.023%

    No Known Activations