© 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. 12342
    Prev
    Next
    INDEX
    Explanations

    assistance with

    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
    横
    -0.28
    æ©«
    -0.24
    åijĹ
    -0.21
    çīĩ
    -0.20
    åĪĿ
    -0.19
    åĻ¨ä»¶
    -0.19
    åħ¨
    -0.19
    å¾Ģä¸Ĭ
    -0.18
    å·²æľī
    -0.18
    _border
    -0.18
    POSITIVE LOGITS
    è¯Ŀé¢ĺ
    0.23
    çļĦè¯Ŀé¢ĺ
    0.22
    çĸijéĹ®
    0.21
    ÇĶ
    0.21
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.21
    éĹ®æĪij
    0.20
    åı¦ä¸Ģè¾¹
    0.20
    æ·¦
    0.19
    è¿Ļ个éĹ®é¢ĺ
    0.19
    çĻ»å±±
    0.19
    Activations Density 0.002%

    No Known Activations