© 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. 5598
    Prev
    Next
    INDEX
    Explanations

    speaking to you

    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
    ä¸į失
    -0.09
    åıĺå¾ĹæĽ´åĬł
    -0.09
    çĶŁäº§è®¾å¤ĩ
    -0.09
    fest
    -0.09
    å·¥ä½ľç»Ħ
    -0.08
    ä¸ŃåĽ½å¤§éĻĨ
    -0.08
    ä»ħä¾Ľ
    -0.08
    ä¾ĿçĦ¶æĺ¯
    -0.08
    official
    -0.08
    ระว
    -0.08
    POSITIVE LOGITS
    éĥ½çŁ¥éģĵ
    0.20
    åIJ¬è¯´è¿ĩ
    0.19
    ä¹ŁçŁ¥éģĵ
    0.15
    æĪijä»¬çŁ¥éģĵ
    0.14
    çľĭè¿ĩ
    0.14
    ä¼ĹæīĢåij¨çŁ¥
    0.14
     familiar
    0.14
    åIJ¬è¿ĩ
    0.14
    çĨŁæĤī
    0.13
    è§ģè¿ĩ
    0.13
    Activations Density 0.108%

    No Known Activations