© 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. 21095
    Prev
    Next
    INDEX
    Explanations

    health and safety concerns

    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
    ä½IJ
    -0.09
    çĭİ
    -0.09
    æĭ³
    -0.09
     Hollow
    -0.08
    åĽŀåij³
    -0.08
    æľºåħ³
    -0.08
    filer
    -0.08
    ä¸įå¾Ĺè¶ħè¿ĩ
    -0.08
    è£ģå®ļ
    -0.08
    odial
    -0.08
    POSITIVE LOGITS
    è¢Ħ
    0.11
    /downloads
    0.10
    /environment
    0.10
    轻轻
    0.09
    _PRESENT
    0.09
    عÙĬÙĨ
    0.09
    åĨ¯
    0.09
     окÑĢÑĥжа
    0.09
    æľīæ¯Ĵ
    0.09
    inks
    0.09
    Activations Density 0.058%

    No Known Activations