© 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. 47899
    Prev
    Next
    INDEX
    Explanations

    off the coast

    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
    amer
    -0.09
    åºĬä¸Ĭ
    -0.09
     Porto
    -0.09
    AMB
    -0.09
    åı£è¢ĭ
    -0.08
    代åĬŀ
    -0.08
    uÅŁ
    -0.08
     GANG
    -0.08
     _$
    -0.08
    åºĬ
    -0.08
    POSITIVE LOGITS
    éĨĴ缮
    0.10
     Jarvis
    0.10
    æ¦Ľ
    0.10
    wake
    0.09
    éĺ¡
    0.09
    笪
    0.09
    /on
    0.09
    æł·æĿ¿
    0.09
    erman
    0.08
    åĪ¶æĪIJ
    0.08
    Activations Density 0.019%

    No Known Activations