© 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. 50448
    Prev
    Next
    INDEX
    Explanations

    organization names or acronyms

    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
    emet
    -0.10
    æŁ³
    -0.10
     Rag
    -0.09
     Sug
    -0.09
    vig
    -0.09
    交éĻħ
    -0.09
    chos
    -0.09
    emen
    -0.08
    ä¸ĭæ²ī
    -0.08
    ä¾ĥ
    -0.08
    POSITIVE LOGITS
    åĴĮ个人
    0.11
    æĬ¥ä¸ļ
    0.11
    æĽĿ
    0.09
    è¾Ī
    0.09
    åĮĸçļĦ
    0.09
    mentation
    0.09
    輩
    0.09
    à¸ļà¸Ĺ
    0.08
    æŃĩ
    0.08
    è¿·
    0.08
    Activations Density 0.002%

    No Known Activations