© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61301
    Prev
    Next
    INDEX
    Explanations

    names like Manson, Mandal, and Mangalore

    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
    леÑĩ
    -0.10
    责任æĦŁ
    -0.09
    æģ¯æģ¯
    -0.09
    uyá»ģn
    -0.09
    åħļ建
    -0.09
    åĩºå¤Ħ
    -0.08
    åĺĺ
    -0.08
    åIJĪä¸Ģ
    -0.08
     hors
    -0.08
    主宰
    -0.08
    POSITIVE LOGITS
    ctal
    0.10
    å¿Ĵ
    0.09
    ember
    0.08
    onis
    0.08
    owing
    0.08
    ou
    0.08
    kte
    0.08
    ÑĪка
    0.08
    _fatal
    0.08
    çĴĩ
    0.08
    Activations Density 0.004%

    No Known Activations