© 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. 58309
    Prev
    Next
    INDEX
    Explanations

    under certain circumstances

    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
    éĺµèIJ¥
    -0.09
    ovsky
    -0.09
    chie
    -0.09
    piring
    -0.08
    avs
    -0.08
     yanı
    -0.08
    æĹ©æĹ©
    -0.08
    è¿Ļä¹Łæĺ¯
    -0.08
    è¿Ļè¾¹
    -0.08
    eren
    -0.08
    POSITIVE LOGITS
     circumstances
    0.29
     circumstance
    0.20
    æĥħåĨµä¸ĭ
    0.19
    æĥħåĨµ
    0.17
    æĿ¡ä»¶ä¸ĭ
    0.17
     conditions
    0.17
    æĿ¡ä»¶
    0.16
    æĥħæ³ģ
    0.14
    Conditions
    0.14
     situation
    0.13
    Activations Density 0.044%

    No Known Activations