© 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. 1911
    Prev
    Next
    INDEX
    Explanations

    stopping, reduction, or cessation

    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
    磼
    -0.27
    éĥ
    -0.24
     Contr
    -0.23
    æıIJè®®
    -0.23
    好å¥ĩ
    -0.23
     impatient
    -0.22
     hypo
    -0.22
    èĴ¯
    -0.22
    irst
    -0.21
    ristol
    -0.21
    POSITIVE LOGITS
     until
    0.31
    until
    0.29
     till
    0.29
     Until
    0.29
    两年
    0.28
    ä¸ĢçĽ´æ²¡æľī
    0.28
    Until
    0.27
     temporarily
    0.27
    ä¸Ģ缴æĺ¯
    0.27
    缴åĪ°
    0.26
    Activations Density 0.400%

    No Known Activations