© 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. 34490
    Prev
    Next
    INDEX
    Explanations

    internet slang and emoticons

    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
     btw
    -0.08
     Beau
    -0.08
    pps
    -0.08
    人éĥ½
    -0.08
    æĪĺéĺŁ
    -0.08
    andal
    -0.08
    åĺĽ
    -0.08
    Pane
    -0.08
    inder
    -0.08
    MA
    -0.08
    POSITIVE LOGITS
    举æĬ¥
    0.10
    èµŀèµı
    0.09
    éĽī
    0.09
    asma
    0.08
    _NOP
    0.08
    åĢ¾åIJij
    0.08
    åıĮéĩį
    0.08
    ç¼ĺåĪĨ
    0.08
    ÑģÑĮ
    0.08
    neys
    0.08
    Activations Density 0.011%

    No Known Activations