© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36670
    Prev
    Next
    INDEX
    Explanations

    situated followed by location prepositions

    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
    ../../../
    -0.09
    éĹ¾
    -0.09
    æĪij没æľī
    -0.08
    Åij
    -0.08
    owell
    -0.08
    pler
    -0.08
    é»ij马
    -0.08
    ister
    -0.08
    à¸īà¸ļ
    -0.08
     sheer
    -0.08
    POSITIVE LOGITS
    urator
    0.11
    åŃIJéĩĮ
    0.10
    urally
    0.10
    igli
    0.10
    ãĥ¡ãĥ³ãĥĪ
    0.09
    ément
    0.09
    MENT
    0.09
    åľ¨äº¬
    0.09
    åIJĪéĢĤ
    0.09
    uate
    0.09
    Activations Density 0.021%

    No Known Activations