© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51120
    Prev
    Next
    INDEX
    Explanations

    bank of world places

    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
    idos
    -0.09
    imos
    -0.09
    BERS
    -0.08
    icom
    -0.08
    rias
    -0.08
     Wich
    -0.08
    ERC
    -0.08
    æľīæĿ¡ä»¶çļĦ
    -0.08
    aji
    -0.08
    亲æĪļ
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ人
    0.09
    rupt
    0.09
    大äºİ
    0.08
    è§īå¾Ĺå¾Ī
    0.08
    åIJ¹
    0.08
     Bever
    0.08
     Chr
    0.08
    å°ıçĶ·åŃ©
    0.08
    Å«
    0.08
    ramid
    0.08
    Activations Density 0.007%

    No Known Activations