© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 251
    Prev
    Next
    INDEX
    Explanations

    individual items or amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    éĺ¶
    -0.29
    ulta
    -0.27
    éĽĨåIJĪ
    -0.27
    å²ģæľĪ
    -0.24
    yr
    -0.24
     CHARSET
    -0.23
    å¹´èµ·
    -0.23
    代
    -0.23
    å¤ļç§į
    -0.23
    åħ¼å®¹
    -0.22
    POSITIVE LOGITS
     individual
    0.40
     individually
    0.37
     Individual
    0.33
     pairs
    0.32
     individ
    0.31
    _individual
    0.31
    individual
    0.29
    pairs
    0.29
     lids
    0.28
    Individual
    0.28
    Activations Density 0.100%

    No Known Activations