© 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. 21903
    Prev
    Next
    INDEX
    Explanations

    downtown followed by city

    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
    lessly
    -0.10
    entially
    -0.09
    对ä¸įèµ·
    -0.09
    æĿ¥èĩª
    -0.09
    oad
    -0.08
    als
    -0.08
     gì
    -0.08
    жд
    -0.08
    亢
    -0.08
    Runnable
    -0.08
    POSITIVE LOGITS
    ä¹ĭä½ľ
    0.09
    ÙĪع
    0.09
    oids
    0.09
    æīĢæľī人
    0.08
    -most
    0.08
    Ñīе
    0.08
    -east
    0.08
    æĹ¢è¦ģ
    0.08
    éĺ¿æĭī
    0.08
    มà¸Ļ
    0.08
    Activations Density 0.005%

    No Known Activations