© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9332
    Prev
    Next
    INDEX
    Explanations

    gas well

    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
    çĽĨåľ°
    -0.12
    缴åįĩ
    -0.11
    пÑĢÑı
    -0.11
    asics
    -0.10
    æı´
    -0.10
    é¹ı
    -0.10
    滹
    -0.10
    è¡Ļ
    -0.09
    antity
    -0.09
    .intent
    -0.09
    POSITIVE LOGITS
    ä¸ĢåĿĹ
    0.09
    åºŁå¼ĥ
    0.09
     som
    0.08
    è¿ĻåĿĹ
    0.08
    æĵĤ
    0.08
    å¼ĥ
    0.08
    Gar
    0.08
     spin
    0.08
    åı¶çīĩ
    0.08
    Spin
    0.08
    Activations Density 0.055%

    No Known Activations