© 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. 3157
    Prev
    Next
    INDEX
    Explanations

    cultural societies, primitive, expanded, community

    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
    èī¯
    -0.09
    åĩĮ
    -0.09
    íijľ
    -0.09
    åľ°æĿ¿
    -0.09
    é¡ı
    -0.09
    èĢķèĢĺ
    -0.08
    ä¹ĭæĪĺ
    -0.08
    åķĨä¸ļåľ°äº§
    -0.08
     пок
    -0.08
    ç»ıèIJ¥çIJĨ念
    -0.08
    POSITIVE LOGITS
    æ°Ķè¡Ģ
    0.09
     powers
    0.08
    çŃ
    0.08
    è§ħ
    0.08
    éĹ³
    0.08
     systems
    0.08
    éĢıè§Ĩ
    0.08
    æµģåĬ¨æĢ§
    0.08
    ä¸įå¼Ģ
    0.08
    å·«
    0.08
    Activations Density 0.090%

    No Known Activations