© 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. 37972
    Prev
    Next
    INDEX
    Explanations

    importance and worth

    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
    åĬ¾
    -0.09
    éĵ¨
    -0.08
    åIJĦå¼ı
    -0.08
    å¤ļç§į
    -0.08
    è¡Į使
    -0.08
    çIJĨæĢ§
    -0.08
    æŃ»è§Ĵ
    -0.08
    åIJĮ缣
    -0.08
    温馨
    -0.08
    æ¸ħéĨĴ
    -0.08
    POSITIVE LOGITS
    ä»·åĢ¼
    0.13
    åĥ¹åĢ¼
    0.12
    æľīä»·åĢ¼
    0.11
     importance
    0.11
    çļĦéĩįè¦ģæĢ§
    0.11
    æľīä»·åĢ¼çļĦ
    0.10
    çĥĺå¹²
    0.10
    åľ¨ç½ij绾
    0.10
    个ä½ĵ
    0.10
    bü
    0.10
    Activations Density 0.072%

    No Known Activations