© 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. 16099
    Prev
    Next
    INDEX
    Explanations

    blog post diary entry

    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
    åģļ强
    -0.24
    è·
    -0.21
    毫æĹłçĸij
    -0.21
    ijing
    -0.21
    çĤĻ
    -0.20
    åı¼
    -0.20
    éĺī
    -0.20
    ARGET
    -0.19
    åĴĮæĶ¯æĮģ
    -0.19
     propTypes
    -0.19
    POSITIVE LOGITS
    æĹ¥è®°
    0.33
     nháºŃt
    0.26
    chron
    0.26
    è®°å½ķ
    0.26
    è¨ĺéĮĦ
    0.25
    è®°
    0.24
     documenting
    0.23
    ä¸Ģ段
    0.23
    record
    0.22
    ãģĬãģĭ
    0.22
    Activations Density 0.089%

    No Known Activations