© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2190
    Prev
    Next
    INDEX
    Explanations

    vehicle driving condition

    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
    强æľīåĬĽçļĦ
    -0.25
    ç®Ķ
    -0.25
    ä¾µèļĢ
    -0.25
     usher
    -0.24
    çļĦæĶ¯æĮģ
    -0.24
    æ·±å±Ĥ次
    -0.24
    åĴĮæĶ¯æĮģ
    -0.24
     backstage
    -0.24
     storyboard
    -0.24
    åŃĺåľ¨äºİ
    -0.24
    POSITIVE LOGITS
     mileage
    0.34
    è¡Į驶
    0.34
    è·¯åĨµ
    0.33
     kWh
    0.33
    å¼Ģ车
    0.32
    çĶ¨è½¦
    0.32
    å·¡èĪª
    0.31
    æŃ£å¸¸ä½¿çĶ¨
    0.31
    ä¿Ŀåħ»
    0.31
     averages
    0.30
    Activations Density 0.019%

    No Known Activations