© 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. 20825
    Prev
    Next
    INDEX
    Explanations

    offers or deals

    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
    æĭį
    -0.09
     Alive
    -0.08
    æĪijçľĭ
    -0.08
    ic
    -0.08
    èł¹
    -0.08
    ãģĭãģª
    -0.08
    Ele
    -0.08
    .backend
    -0.08
    çIJĨ解åĴĮ
    -0.08
     chap
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ
    0.10
    åĨ³å¿ĥ
    0.10
    -any
    0.10
    ä»»ä½ķä¸Ģ个
    0.09
    .Requires
    0.09
    à¤ĵ
    0.09
    èĭ¾
    0.09
     Rehabilitation
    0.09
    çİ°åŃĺ
    0.09
    åIJ¦
    0.09
    Activations Density 0.046%

    No Known Activations