© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26483
    Prev
    Next
    INDEX
    Explanations

    Street and avenue names

    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
    allis
    -0.09
    ilog
    -0.09
    lew
    -0.08
     vit
    -0.08
    çīµå¼ķ
    -0.08
    æīĺ管
    -0.08
    åįģ足
    -0.08
    æĢ§å¼º
    -0.08
    éĩī
    -0.08
    åįļ主
    -0.08
    POSITIVE LOGITS
    ิà¸ĩ
    0.09
    çĭŃ
    0.09
    craft
    0.09
    Facade
    0.09
    anners
    0.09
    ÑĢÑĥÑĤ
    0.09
    tran
    0.09
    ä»»ä½ķ人éĥ½
    0.09
    åıįä¹ĭ
    0.08
    èĢ½
    0.08
    Activations Density 0.010%

    No Known Activations