© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16094
    Prev
    Next
    INDEX
    Explanations

    meeting needs and requirements

    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
    对è¯Ŀ
    -0.20
     way
    -0.19
    éķĨ
    -0.19
    çĶŁæ´»æĸ¹å¼ı
    -0.19
    æĽ¿
    -0.19
    åĢ®
    -0.18
    è¿Ļç§įæĸ¹å¼ı
    -0.18
    onto
    -0.18
    åľ°æ®µ
    -0.18
    PTS
    -0.18
    POSITIVE LOGITS
    éľĢæ±Ĥ
    0.41
     needs
    0.41
    è¦ģæ±Ĥ
    0.38
     Needs
    0.35
     requirements
    0.35
    çļĦè¦ģæ±Ĥ
    0.34
    客æĪ·éľĢæ±Ĥ
    0.33
    å¸ĤåľºéľĢæ±Ĥ
    0.32
    needs
    0.32
    Needs
    0.31
    Activations Density 0.083%

    No Known Activations