© 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. 52507
    Prev
    Next
    INDEX
    Explanations

    USB device or connection

    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
    ial
    -0.10
    edList
    -0.10
    rone
    -0.10
    é¼ĵèĪŀ
    -0.09
    è°Ĩ
    -0.09
    تÙħ
    -0.08
    nement
    -0.08
    ész
    -0.08
    ools
    -0.08
    IMUM
    -0.08
    POSITIVE LOGITS
    æĴ¼
    0.09
    å¡ŀ
    0.09
    _De
    0.09
    ify
    0.08
    ä»ĬåĽŀ
    0.08
    ãģĦãģĨ
    0.08
    ย
    0.08
    ClassLoader
    0.08
    è¿Ļ次
    0.08
     оÑĤноÑĪении
    0.08
    Activations Density 0.019%

    No Known Activations