© 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. 11066
    Prev
    Next
    INDEX
    Explanations

    no matter what

    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
    anke
    -0.09
    ç½ķ
    -0.09
    ä¸įå¿ħè¦ģçļĦ
    -0.09
    _PED
    -0.09
    ä¾µ
    -0.08
    ProgressHUD
    -0.08
    对æĪij们
    -0.08
    移éĢģ
    -0.08
    æľª
    -0.08
     LENG
    -0.08
    POSITIVE LOGITS
    åĬªåĬĽ
    0.12
     efforts
    0.10
     attempts
    0.10
    ä»ĺåĩº
    0.10
    è°Ĩ
    0.10
    åĬª
    0.09
    å¤ļ次
    0.09
     repeatedly
    0.09
    th
    0.09
    æĭ¼åij½
    0.09
    Activations Density 0.092%

    No Known Activations