© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26387
    Prev
    Next
    INDEX
    Explanations

    location names after 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
    erged
    -0.09
    å³ģ
    -0.08
    ternal
    -0.08
    管çIJĨåĴĮ
    -0.08
    åıĬåħ¶
    -0.08
    åĽłåħ¶
    -0.08
    ermann
    -0.08
    ä¸įåħĭ
    -0.07
    ror
    -0.07
    æĭĨ
    -0.07
    POSITIVE LOGITS
    è¡«
    0.10
    èĭ±æīį
    0.10
    è°´
    0.09
    壯
    0.09
    è¯ķéªĮåĮº
    0.09
    пÑĥ
    0.09
    å°±èĥ½
    0.09
    ç½ķ
    0.09
    éĤ£ä¸ĢåĪ»
    0.09
    åIJ¬å®Į
    0.08
    Activations Density 0.202%

    No Known Activations