© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20438
    Prev
    Next
    INDEX
    Explanations

    mobile

    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
    enen
    -0.10
    æľĢåħĪ
    -0.09
    çĤĸ
    -0.09
    Paren
    -0.09
    èĶ
    -0.08
    åIJĪæ³ķ
    -0.08
    å¼Ģ端
    -0.08
     seks
    -0.08
    å°±è¿ij
    -0.08
    eax
    -0.08
    POSITIVE LOGITS
    移åĬ¨
    0.17
    å¤ĸåĩº
    0.15
     mobile
    0.13
    æĹħ
    0.13
     nom
    0.12
    åĽĽå¤Ħ
    0.12
    æĹħè¡Į
    0.12
    带走
    0.12
    移åĬ¨ç«¯
    0.12
    Mobile
    0.11
    Activations Density 0.148%

    No Known Activations