© 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. 1802
    Prev
    Next
    INDEX
    Explanations

    ending or stopping

    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
    _encoded
    -0.25
    ibaba
    -0.24
    ç³Ļ
    -0.22
    urpose
    -0.22
    ç½Ķ
    -0.21
    äºĮ代
    -0.21
    ippers
    -0.21
     иг
    -0.21
     flyer
    -0.21
     epit
    -0.21
    POSITIVE LOGITS
    å¤ĩçĶ¨
    0.26
     rests
    0.24
    (stop
    0.24
    åģľä¸ĭæĿ¥
    0.24
     tắt
    0.24
    è®°
    0.23
    åģľä¸ĭ
    0.23
     â
    0.23
    æ²
    0.22
    继ç»Ń
    0.22
    Activations Density 0.004%

    No Known Activations