© 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. 326
    Prev
    Next
    INDEX
    Explanations

    AI opponents

    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
    åīįéĢĶ
    -0.26
    .instagram
    -0.25
     Incident
    -0.24
     <
    -0.24
    该éĻ¢
    -0.23
    ripple
    -0.23
    沧
    -0.22
    èIJ½åľ°
    -0.22
    éģį
    -0.21
     requested
    -0.21
    POSITIVE LOGITS
    对æīĭ
    0.35
     intelligence
    0.31
    intelligence
    0.28
    人çī©
    0.27
    iali
    0.27
    .AI
    0.27
     Parr
    0.27
     AI
    0.27
     opponents
    0.26
    AGENT
    0.26
    Activations Density 0.019%

    No Known Activations