© 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. 11574
    Prev
    Next
    INDEX
    Explanations

    industry news, events, and websites

    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
    æıĨ
    -0.09
    çĿģ
    -0.09
    äºī
    -0.08
    温馨æıIJ示
    -0.08
    ä»ĸè¿ĺ
    -0.08
    å°ıåĮº
    -0.08
    éĨĭ
    -0.08
    åĽ½åĬ¡
    -0.08
    èĩªçĦ¶çģ¾å®³
    -0.08
    éªij
    -0.08
    POSITIVE LOGITS
    rades
    0.10
    INGTON
    0.09
    æ´ŀå¯Ł
    0.09
    ç»ĨåĪĨ
    0.09
    ATTER
    0.09
    æĬķèŀįèµĦ
    0.08
     Professionals
    0.08
     ÙĨÙĤ
    0.08
    ORTH
    0.08
    profession
    0.08
    Activations Density 0.081%

    No Known Activations