© 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. 49111
    Prev
    Next
    INDEX
    Explanations

    as something / an / a

    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
    ç®Ĺæĺ¯
    -0.10
    é¢ĦåĪ¶
    -0.10
    compass
    -0.09
    çľĭä¼¼
    -0.09
     JMP
    -0.09
     critique
    -0.08
    被称为
    -0.08
    æ¸ħæĺİ
    -0.08
    æĽ²æĬĺ
    -0.08
    è°ģçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    æµģ
    0.10
    URN
    0.10
    ä¸ĢéŨ
    0.10
    æŁIJç§į
    0.10
    éĴĩ
    0.10
    andas
    0.09
    宾客
    0.09
    anda
    0.09
    å¹²ä»Ģä¹Ī
    0.09
    ä¸Ģåij³
    0.09
    Activations Density 0.098%

    No Known Activations