© 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. 18541
    Prev
    Next
    INDEX
    Explanations

    standard naming conventions

    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
     Enough
    -0.09
    enet
    -0.09
    еÑĨ
    -0.09
    åĢª
    -0.08
     Moran
    -0.08
    èĢĮä¸į
    -0.08
    esome
    -0.08
    æīĭåĨĮ
    -0.08
     tanto
    -0.08
    isoft
    -0.08
    POSITIVE LOGITS
    æѤ类
    0.12
    ами
    0.09
    èĩªä¸»
    0.09
    çĴĩ
    0.09
    å¦Ĥæŀľæĺ¯
    0.09
    è¿Ļä¸ĢåĪ»
    0.09
     replic
    0.08
    agen
    0.08
    个ä½ĵ
    0.08
    äºĭçī©
    0.08
    Activations Density 0.188%

    No Known Activations