© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52620
    Prev
    Next
    INDEX
    Explanations

    contacting or approaching entities

    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
    æķĻè®Ń
    -0.09
    ears
    -0.09
    æĹĦ
    -0.08
    è·³è·ĥ
    -0.08
    asd
    -0.08
    mpl
    -0.08
    IFE
    -0.08
    æķ´é¡¿
    -0.08
    -Identifier
    -0.08
    é¦ĸ
    -0.08
    POSITIVE LOGITS
    èģĶç³»
    0.21
    èģĶç³»æĸ¹å¼ı
    0.17
     contacts
    0.17
    æīĵçĶµè¯Ŀ
    0.16
     contacting
    0.16
     contact
    0.16
    æĭľè®¿
    0.16
    éĹ®éĹ®
    0.15
    åķıãģĦåIJĪãĤıãģĽ
    0.15
    询éĹ®
    0.14
    Activations Density 0.092%

    No Known Activations