© 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. 51124
    Prev
    Next
    INDEX
    Explanations

    minimally invasive as possible

    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
    æľīäºĨ
    -0.09
    鬻
    -0.08
    亵
    -0.08
     Terr
    -0.08
    ä½İä½į
    -0.08
    onder
    -0.08
     worse
    -0.08
    ëĶ°
    -0.07
    BUILD
    -0.07
     Kale
    -0.07
    POSITIVE LOGITS
    å°½åı¯èĥ½
    0.19
    å°½éĩı
    0.18
     wherever
    0.11
    å°½æĹ©
    0.10
    æĺ¯æľĢ好çļĦ
    0.10
    _NC
    0.10
    åıªæľīä¸Ģ个
    0.10
    ä¸įè¦ģ太
    0.10
    åĵªæĢķ
    0.10
     whenever
    0.10
    Activations Density 0.079%

    No Known Activations