© 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. 9489
    Prev
    Next
    INDEX
    Explanations

    sharp knife

    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
    欣æħ°
    -0.09
    幡
    -0.09
    ende
    -0.09
    移交
    -0.09
    -animate
    -0.08
    çIJ¼
    -0.08
    elow
    -0.08
    æī¹
    -0.08
    æĸĩæĺĮ
    -0.08
    项éĵ¾
    -0.08
    POSITIVE LOGITS
    éĴĿ
    0.13
    æĪĹ
    0.10
    riting
    0.09
    çĵľ
    0.09
    å¹²éĥ¨éĺŁä¼į
    0.09
    åĪĥ
    0.09
    åIJĦ级
    0.09
    ç¡ķ
    0.09
    åĪĢ
    0.09
     slice
    0.09
    Activations Density 0.019%

    No Known Activations