© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19460
    Prev
    Next
    INDEX
    Explanations

    guiding and shaping actions

    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
    è¿Ļ个éĹ®é¢ĺ
    -0.11
    æĸĵ
    -0.10
    ave
    -0.09
    对æĪij说
    -0.09
    æĪij说
    -0.09
    esis
    -0.09
    æ¥ŀ
    -0.09
    æĴĤ
    -0.09
    éĤĵå°ı
    -0.09
    éĥ½è®¤ä¸º
    -0.08
    POSITIVE LOGITS
     decisions
    0.12
     choices
    0.10
     shaping
    0.09
    åĨ³çŃĸ
    0.09
    è¡Įäºĭ
    0.08
    SHA
    0.08
    缴èĩ³
    0.08
    å·¦åı³
    0.08
     Presbyterian
    0.08
    æĮĩå¼ķ
    0.08
    Activations Density 0.090%

    No Known Activations