© 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. 14949
    Prev
    Next
    INDEX
    Explanations

    history of

    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
    ืà¸Ńà¸Ļ
    -0.18
    éľĢ
    -0.18
    è·ijéģĵ
    -0.18
    嵯
    -0.18
    å½ĵæĹ¥
    -0.18
    ULO
    -0.18
    erie
    -0.17
    éĢIJå¹´
    -0.17
    å½ĵåľ°æĶ¿åºľ
    -0.17
    åŁĴ
    -0.17
    POSITIVE LOGITS
    sWith
    0.22
    以ä¾Ĩ
    0.20
    è¿ĻæĶ¯
    0.19
    åľ¨æĪijåĽ½
    0.18
    çĽ¸ä¼ł
    0.18
    ipt
    0.17
    deg
    0.17
     stag
    0.17
    æĬĺèħ¾
    0.17
    çļĦä¸Ģ款
    0.17
    Activations Density 0.056%

    No Known Activations