© 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. 26865
    Prev
    Next
    INDEX
    Explanations

    based on the

    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
    导读
    -0.08
    åħ¶å®ĥ
    -0.08
    åĽºçĦ¶
    -0.07
     Mex
    -0.07
    å±Ģéĥ¨
    -0.07
    æĻĴ
    -0.07
    æĢĴ
    -0.07
    ardless
    -0.07
    ä¹ı
    -0.07
    çī¹æĢ§
    -0.07
    POSITIVE LOGITS
    è¿Ļ段
    0.12
    è¯Ńæ°Ķ
    0.11
    .sg
    0.11
    请éĹ®
    0.10
     Richardson
    0.10
    éĻĪè¿°
    0.09
     SENT
    0.09
    æĭŁ
    0.09
    æĸĩä¸Ń
    0.09
    è´¨éĩı管çIJĨ
    0.09
    Activations Density 0.233%

    No Known Activations