© 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. 403
    Prev
    Next
    INDEX
    Explanations

    possible, probable, supposed

    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
     enough
    -0.35
     Enough
    -0.27
    Enough
    -0.27
    人å¿ĥ
    -0.25
    人寿
    -0.24
    ä¸įå·²
    -0.23
    æĬ¤èº«
    -0.23
    ened
    -0.22
    athing
    -0.22
     pens
    -0.22
    POSITIVE LOGITS
     maximum
    0.28
    å·²ä¹ħçļĦ
    0.27
     conflict
    0.25
     thereof
    0.25
     consequences
    0.25
     differences
    0.25
    mente
    0.24
     gaps
    0.24
     threats
    0.24
     dangers
    0.24
    Activations Density 0.086%

    No Known Activations