© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14928
    Prev
    Next
    INDEX
    Explanations

    import tax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     Pope
    -0.20
    æ£ł
    -0.20
    媳
    -0.19
    çĤ¹åįĬ
    -0.19
     모ìĬµ
    -0.18
     spilled
    -0.18
     candid
    -0.18
     Marl
    -0.18
    lop
    -0.18
     pir
    -0.18
    POSITIVE LOGITS
    è´¹çĶ¨
    0.25
    å¼Ĥè®®
    0.24
    æīĭç»Ń
    0.23
    äºĭ项
    0.23
    ä¸ĩä¸Ģ
    0.22
    ä½łéľĢè¦ģ
    0.22
    å¿ħè¦ģ
    0.22
    åıĸåĨ³äºİ
    0.22
    åĽłç´ł
    0.22
    äºĭåħĪ
    0.22
    Activations Density 0.036%

    No Known Activations