© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37139
    Prev
    Next
    INDEX
    Explanations

    rise and fall

    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
    æĤ£
    -0.09
    ä¸Ģå±Ĥ
    -0.09
    ä¸Ģç§Ĵ
    -0.09
    locks
    -0.08
     Gül
    -0.08
    bow
    -0.08
    æĪĸå¤ļ
    -0.08
    æĪĪ
    -0.08
    æľīå¿ħè¦ģ
    -0.08
    ICA
    -0.08
    POSITIVE LOGITS
    å´Ľèµ·
    0.13
     ÑģобÑģÑĤвенно
    0.10
    -rise
    0.10
    èµ·æĿ¥
    0.10
    åıĮåıĮ
    0.10
    åĴĮåıijå±ķ
    0.10
    äºĨä¸Ģæī¹
    0.09
    \Facades
    0.09
    éªĸ
    0.09
    áŀ¡
    0.09
    Activations Density 0.019%

    No Known Activations