© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 241
    Prev
    Next
    INDEX
    Explanations

    look to verb or noun

    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
    stands
    -0.25
    ignment
    -0.25
    éĥļ
    -0.23
    èĢı
    -0.23
    oub
    -0.22
    峿
    -0.21
     suspected
    -0.21
    éģĨ
    -0.21
     willingly
    -0.20
    çĪĶ
    -0.20
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.39
    å·²ä¹ħ
    0.30
    ãģ¦ãĤĤ
    0.23
    ed
    0.23
    OrCreate
    0.22
    lessly
    0.22
    æĽĻ
    0.21
     changes
    0.20
    ate
    0.20
    èĪĮ
    0.20
    Activations Density 0.026%

    No Known Activations