© 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. 219
    Prev
    Next
    INDEX
    Explanations

    your device

    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
    æł·æĿ¿
    -0.29
    nuts
    -0.26
    å¹´ä¹ĭ
    -0.26
    å©»
    -0.25
    ä¾´
    -0.25
    ernals
    -0.25
    çī¹æ®ĬæĥħåĨµ
    -0.25
    ç»ĵæŀĦæĢ§
    -0.25
    abo
    -0.24
     Nack
    -0.24
    POSITIVE LOGITS
     browser
    0.35
     tablet
    0.33
     device
    0.31
     screen
    0.31
     local
    0.31
    æľ¬åľ°
    0.31
     devices
    0.30
     computer
    0.30
     phone
    0.29
    æµıè§ĪåĻ¨
    0.29
    Activations Density 0.061%

    No Known Activations