© 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. 205
    Prev
    Next
    INDEX
    Explanations

    vehicle suspension and ride quality

    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
     Unicode
    -0.29
    空çĻ½
    -0.27
    Unicode
    -0.27
    åı£å¤´
    -0.25
    Inform
    -0.25
     multiplication
    -0.25
    éķ¿å¯¿
    -0.25
    åı£
    -0.24
    æ´Ĺæīĭ
    -0.24
     inform
    -0.24
    POSITIVE LOGITS
     stiffness
    0.43
    åºķçĽĺ
    0.38
     braking
    0.34
    弹簧
    0.33
     damping
    0.33
     chassis
    0.33
    åĪ¶åĬ¨
    0.32
    平衡
    0.31
    åĪ¹è½¦
    0.31
     vibrations
    0.31
    Activations Density 0.032%

    No Known Activations