© 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. 62316
    Prev
    Next
    INDEX
    Explanations

    Valentine's day

    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±IJ
    -0.12
    丰
    -0.11
     Wak
    -0.10
    æ¶Ī
    -0.09
    ä¸Ģ家
    -0.09
    好å¥ĩ
    -0.09
    绳
    -0.09
    ä¹¡åľŁ
    -0.09
    å¸Ĩ
    -0.09
    好å¥ĩå¿ĥ
    -0.09
    POSITIVE LOGITS
    æĥħ人èĬĤ
    0.15
    é¹Ĭ
    0.10
    æķĻèģĮå·¥
    0.10
    èĬ±çĵ£
    0.10
     Valentine
    0.10
    æĥħä¾£
    0.09
    èĬ±æľµ
    0.09
    æģĭçĪ±
    0.09
    çĪ±æĥħ
    0.09
    æ°ijæĶ¿
    0.09
    Activations Density 0.034%

    No Known Activations