© 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. 20684
    Prev
    Next
    INDEX
    Explanations

    the + number or noun

    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¿Ļæł·çļĦè¯Ŀ
    -0.10
    éĻķ
    -0.10
    alli
    -0.10
    读åIJİ
    -0.09
    _salt
    -0.09
    iates
    -0.09
    tern
    -0.09
    è¢Ń
    -0.09
    éĽ¾
    -0.09
     nineteenth
    -0.09
    POSITIVE LOGITS
    åľ¨æĪij
    0.09
    eus
    0.08
    å·§
    0.08
    å°±æľī
    0.08
     slo
    0.08
    èĻ
    0.08
    ä¾®
    0.07
    åľ¨ç½ij绾
    0.07
    nest
    0.07
     nug
    0.07
    Activations Density 0.044%

    No Known Activations