© 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. 56807
    Prev
    Next
    INDEX
    Explanations

    if statements

    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»£æĽ¿
    -0.09
    åıĸåĨ³
    -0.09
    à¸Ħà¸ĩ
    -0.09
    æ²Ľ
    -0.09
     Lucky
    -0.09
    幸
    -0.09
    robat
    -0.09
     Mong
    -0.09
    äºĮ人
    -0.09
    liv
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.14
    ä¸įæĩĤ
    0.12
    æŁIJä¸Ģ
    0.12
    åıijçİ°éĹ®é¢ĺ
    0.11
    æŁIJ个
    0.10
    æľīéĹ®é¢ĺ
    0.10
    åĩºçİ°éĹ®é¢ĺ
    0.10
    åıijçİ°äºĨ
    0.10
    çĶŁçĹħ
    0.10
    ç´¯äºĨ
    0.10
    Activations Density 0.073%

    No Known Activations