© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 806
    Prev
    Next
    INDEX
    Explanations

    conversions and units

    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
    empt
    -0.25
    ç»ĵæŀĦæĢ§
    -0.24
    istrict
    -0.24
    亮çĤ¹
    -0.24
    security
    -0.23
     ÑĥÑģпеÑĪ
    -0.23
    atar
    -0.23
    èĸĦå¼±
    -0.23
    ronics
    -0.23
    åıijèµ·
    -0.22
    POSITIVE LOGITS
     conversions
    0.57
     measurements
    0.57
     measurement
    0.56
    计éĩı
    0.55
     conversion
    0.53
     decimal
    0.53
    æµĭéĩı
    0.50
     Measurement
    0.50
    measurement
    0.49
     units
    0.49
    Activations Density 0.126%

    No Known Activations