© 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. 938
    Prev
    Next
    INDEX
    Explanations

    places, cities, and vacation rentals

    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
    ä¸ī项
    -0.09
    ¹Ħ
    -0.08
    ä¸Ńåħ³
    -0.08
    mented
    -0.08
    åı¨
    -0.08
    ly
    -0.08
    è¦ĨçĽĸ
    -0.08
    åĺŃ
    -0.08
    èĮĶ
    -0.08
    è¿Ļ份
    -0.08
    POSITIVE LOGITS
    åİļåİļ
    0.11
    خش
    0.10
    æĹĴ
    0.09
     hữu
    0.09
    agna
    0.09
    åį¤
    0.09
    alli
    0.09
    riel
    0.09
    ÑĤол
    0.09
    çĶ°
    0.09
    Activations Density 0.001%

    No Known Activations