© 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. 55975
    Prev
    Next
    INDEX
    Explanations

    social interaction and greetings

    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
    OOT
    -0.10
    ä¾£
    -0.09
     blocker
    -0.09
     uç
    -0.09
    ðŁĴ¯
    -0.09
    è¡¡
    -0.09
    åIJ¸åıĸ
    -0.09
    ä½Ķ
    -0.09
    éĢļå¾Ģ
    -0.09
     Abram
    -0.09
    POSITIVE LOGITS
    æı¡æīĭ
    0.16
    èģĶè°Ĭ
    0.13
     handshake
    0.11
    è°Ĭ
    0.11
    éĹ®åĢĻ
    0.11
    社交
    0.11
    觥
    0.10
    æīĵæĭĽåij¼
    0.10
    å¯Ĵ
    0.10
     greeting
    0.09
    Activations Density 0.199%

    No Known Activations