© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    kiss or kissed

    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
    ä¸Ģ个æĺŁæľŁ
    -0.10
    å¤ľéĩĮ
    -0.09
    åħ¨èĥ½
    -0.09
    æ±ŀ
    -0.09
    éŁŃ
    -0.09
    没æľīå¿ħè¦ģ
    -0.09
    arta
    -0.09
     fle
    -0.09
    èī°
    -0.09
    ä¸Ģç»ı
    -0.09
    POSITIVE LOGITS
     kisses
    0.17
     Kiss
    0.16
     kiss
    0.15
     kissing
    0.15
    åIJ»
    0.14
     kissed
    0.14
     baiser
    0.11
    é²ľèĬ±
    0.10
    ðŁĴĭ
    0.10
    æģĭæĥħ
    0.10
    Activations Density 0.023%

    No Known Activations