© 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. 58481
    Prev
    Next
    INDEX
    Explanations

    give it a go

    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
    ingo
    -0.09
    Ale
    -0.09
    éŁŃ
    -0.08
    é¡»
    -0.08
    èĩªä¿¡
    -0.08
    æĶ¾åģĩ
    -0.08
    AV
    -0.08
     Seymour
    -0.08
    éĢīåĩº
    -0.08
    CBC
    -0.08
    POSITIVE LOGITS
    è¯ķè¯ķ
    0.17
    å°Ŀè¯ķ
    0.14
    è¯ķ
    0.13
    åĢ¼å¾Ĺä¸Ģ
    0.13
     thá»Ń
    0.12
    ลà¸Ńà¸ĩ
    0.11
    試
    0.10
    å°Ŀ
    0.10
     Try
    0.10
    _try
    0.10
    Activations Density 0.041%

    No Known Activations