© 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. 1231
    Prev
    Next
    INDEX
    Explanations

    forecasts and predictions

    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
    æľįåĬ¡ä½ĵç³»
    -0.29
     soft
    -0.27
    åij¨è½¬
    -0.26
    çļĦ帮åĬ©
    -0.25
    æľįåĬ¡å¹³åı°
    -0.25
    纡
    -0.25
    软
    -0.24
    èĻIJå¾ħ
    -0.24
    è§ĦèĮĥåĮĸ
    -0.24
    å¹³åı°ä¸Ĭ
    -0.24
    POSITIVE LOGITS
    forecast
    0.32
     forecasts
    0.28
     пÑĢогноз
    0.28
    predictions
    0.27
     forecast
    0.27
    Forecast
    0.27
     Forecast
    0.26
    é¢Ħæµĭ
    0.26
    ä¸įç¡®å®ļæĢ§
    0.26
     predictions
    0.25
    Activations Density 0.011%

    No Known Activations