© 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. 9654
    Prev
    Next
    INDEX
    Explanations

    Missouri legal terms

    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
    çĵ¯
    -0.10
    èݽ
    -0.10
    éľĩ
    -0.09
    è·ĭ
    -0.09
    é©¿ç«Ļ
    -0.09
    æ²Ń
    -0.09
    ä¹¡åľŁ
    -0.09
    è¢ĭ
    -0.09
    泡泡
    -0.08
    .travel
    -0.08
    POSITIVE LOGITS
    éĩįåºĨ
    0.15
    éĩįåºĨå¸Ĥ
    0.13
    anny
    0.11
     Prague
    0.10
    çĥ½
    0.10
    æ¸Ŀ
    0.10
    ÑĤÑı
    0.09
    ASE
    0.09
    ault
    0.09
     kotlin
    0.09
    Activations Density 0.040%

    No Known Activations