© 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. 1391
    Prev
    Next
    INDEX
    Explanations

    will not / ’re not / ’ll not / could not

    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
    ä»ĭç»įäºĨ
    -0.28
    è§ģè¿ĩ
    -0.26
    æŃ£åĢ¼
    -0.25
    说åĪ°è¿ĻéĩĮ
    -0.24
    bd
    -0.23
    (+
    -0.23
     preced
    -0.23
     "+
    -0.23
    ä¹ŁæĽ¾
    -0.23
    äºĨè¿ĩæĿ¥
    -0.23
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.33
    åıªå¥½
    0.31
    è´»
    0.31
    åıªèĥ½
    0.28
    æ··ä¹±
    0.27
     isempty
    0.27
    éļıæĦı
    0.27
    就没æľī
    0.27
    浪费
    0.26
     lã
    0.26
    Activations Density 0.071%

    No Known Activations