© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21132
    Prev
    Next
    INDEX
    Explanations

    preposition to or on followed by noun

    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
    æ¶Ī
    -0.09
    æŃ¹
    -0.08
    åŀ£
    -0.08
    第äºĶå±Ĭ
    -0.08
    åIJį为
    -0.08
    \:
    -0.08
    _DER
    -0.08
     mop
    -0.08
     mur
    -0.08
    inus
    -0.07
    POSITIVE LOGITS
    è¡¥é½IJ
    0.10
    å¾Ĺ罪
    0.10
    åĽ½æĥħ
    0.10
    æľīåħ³è§Ħå®ļ
    0.09
    ensed
    0.09
    ä»Ĺ
    0.09
    ãģĦãĤī
    0.09
    åĽłåľ°åĪ¶å®ľ
    0.09
    riz
    0.09
    isci
    0.09
    Activations Density 0.002%

    No Known Activations