© 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. 8988
    Prev
    Next
    INDEX
    Explanations

    that followed by noun clause

    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
    çī¹æĸ¯
    -0.09
     licensors
    -0.09
    lin
    -0.09
    uese
    -0.09
    çłĶ讨
    -0.08
    atsu
    -0.08
    è´©
    -0.08
     Monterey
    -0.08
    heim
    -0.08
    heel
    -0.08
    POSITIVE LOGITS
    çĭĹ
    0.11
     ìĸ¼ë§ĪëĤĺ
    0.11
    ä½ķå¤Ħ
    0.11
    ä½ķç§į
    0.10
     Cow
    0.10
    ä»Ģä¹Īæł·çļĦ
    0.10
    èı°
    0.10
    å¤ļå°ij
    0.10
    åľ¨åĵª
    0.10
    å¤ļä¹ħ
    0.10
    Activations Density 0.472%

    No Known Activations