© 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. 283
    Prev
    Next
    INDEX
    Explanations

    all cases and populations

    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
    çİ©ç¬ij
    -0.30
    èįĴ
    -0.30
    æ°Ķæ°Ľ
    -0.28
    å¾ħéģĩ
    -0.27
    Always
    -0.26
    Pooling
    -0.25
     меÑħанизм
    -0.24
    çī¹åĪ«
    -0.24
    Others
    -0.24
    解æĶ¾æĢĿæĥ³
    -0.24
    POSITIVE LOGITS
     entire
    0.35
     eligible
    0.33
     relevant
    0.30
     available
    0.28
     currently
    0.28
     imaginable
    0.26
     vertically
    0.26
     sampled
    0.25
    çİ°åŃĺ
    0.25
     worldwide
    0.24
    Activations Density 0.153%

    No Known Activations