© 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. 2604
    Prev
    Next
    INDEX
    Explanations

    fascinating news, things, insight, world

    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
    æĭĽ
    -0.10
    笳
    -0.09
    æī¹è¯Ħ
    -0.08
    åģļåĩº
    -0.08
    é¢ľ
    -0.08
    å»ī
    -0.08
    æıį
    -0.08
    NAMESPACE
    -0.08
    æ³µ
    -0.08
    æĴĤ
    -0.08
    POSITIVE LOGITS
    interesting
    0.20
     interesting
    0.19
    æľī趣
    0.18
     инÑĤеÑĢеÑģ
    0.17
     interess
    0.17
    æľī趣çļĦ
    0.17
     fascinating
    0.16
    Interesting
    0.16
    æĦŁåħ´è¶£
    0.15
    æľīæĦıæĢĿçļĦ
    0.14
    Activations Density 0.076%

    No Known Activations