© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10026
    Prev
    Next
    INDEX
    Explanations

    turf or sod or grass

    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
    oft
    -0.11
    erb
    -0.10
    oti
    -0.09
     Genuine
    -0.09
    ç½ijåıĭè¯Ħ论
    -0.09
    ä¸Ģæ³¢
    -0.09
    isco
    -0.08
     бил
    -0.08
    mare
    -0.08
     parte
    -0.08
    POSITIVE LOGITS
     Ñģебе
    0.09
    erson
    0.09
    зон
    0.09
    atus
    0.08
    айн
    0.08
    ãĤ¡
    0.08
    IER
    0.08
    çļij
    0.08
    acing
    0.08
    indr
    0.08
    Activations Density 0.005%

    No Known Activations