© 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. 15286
    Prev
    Next
    INDEX
    Explanations

    registered user or reservation

    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
    -den
    -0.21
    åĽłåľ°
    -0.20
    æľĢåĪĿçļĦ
    -0.18
    برا
    -0.18
    交åıī
    -0.18
    è¡ĮæĶ¿æľºåħ³
    -0.18
    头çļ®
    -0.18
     Pikachu
    -0.18
    èĦĶ
    -0.18
    æİīäºĨ
    -0.18
    POSITIVE LOGITS
     registered
    0.25
     established
    0.21
    äºĨèĩªå·±çļĦ
    0.20
    åIJĦæľī
    0.20
    为åĩĨ
    0.20
    çĻ»è®°
    0.20
    çIJĨ解
    0.20
    çĬ¶æĢģä¸ĭ
    0.20
    æ·Ģ
    0.19
    åIJĪæł¼
    0.19
    Activations Density 0.042%

    No Known Activations