© 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. 12154
    Prev
    Next
    INDEX
    Explanations

    only

    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
    åı°
    -0.24
    éĽħ
    -0.23
    anus
    -0.21
    odel
    -0.20
    æĪijåĴĮ
    -0.20
    åīįç½®
    -0.19
    梦
    -0.19
    èĢĥèĻijåĪ°
    -0.19
    èĮĥ
    -0.19
    å¤ļåįĬ
    -0.18
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.21
    å°±è¶Ĭ
    0.20
    ä¹Łåıªèĥ½
    0.20
    PLE
    0.19
    ä¸Ģ件äºĭæĥħ
    0.18
    æłijåı¶
    0.18
    BT
    0.18
     Autof
    0.18
     Ont
    0.18
     lw
    0.17
    Activations Density 0.069%

    No Known Activations