© 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. 63091
    Prev
    Next
    INDEX
    Explanations

    submit sell file save enter

    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
    éķ¿è¿ľ
    -0.09
    Reuse
    -0.09
    xis
    -0.09
    åĨįéĢł
    -0.09
    两æĿ¡
    -0.08
    å¤ļå¹´
    -0.08
    æ¯ıä¸Ģ次
    -0.08
    å¾ĹåĪ°äºĨ
    -0.08
    çļĦä¸ĢéĿ¢
    -0.08
    æī¹
    -0.08
    POSITIVE LOGITS
    лÑİб
    0.11
    æīįèĥ½å¤Ł
    0.10
    赶åĪ°
    0.10
    è¦ģä¸įçĦ¶
    0.10
    åIJ¦åĪĻ
    0.10
    æīįèĥ½
    0.09
    赶ä¸Ĭ
    0.09
    赶æĿ¥
    0.09
    åĮĨ
    0.09
    Peak
    0.09
    Activations Density 0.024%

    No Known Activations