© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37985
    Prev
    Next
    INDEX
    Explanations

    in, ab, um suffixes

    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
    åħ±åIJĮåĬªåĬĽ
    -0.10
    æįIJ
    -0.10
    è´¨
    -0.10
    ä¸Ģè§Ī
    -0.10
    被æīĵ
    -0.09
    åįģåĩł
    -0.09
    åĽ¾ä¸º
    -0.09
    常è§ģçļĦ
    -0.09
    é½IJåħ¨
    -0.09
    orts
    -0.09
    POSITIVE LOGITS
    unt
    0.10
    åħ¬æĬ¥
    0.09
    erator
    0.09
    åīįæıIJæĺ¯
    0.08
    çĭ¬
    0.08
     fashion
    0.07
    Unt
    0.07
    èĮ«
    0.07
    omb
    0.07
     sovereign
    0.07
    Activations Density 0.294%

    No Known Activations