© 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. 16200
    Prev
    Next
    INDEX
    Explanations

    professions and roles

    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
    ä»»ä½ķ人
    -0.23
    åīįæĸ¹
    -0.21
    è¶Ĭæĺ¯
    -0.21
    .Perform
    -0.21
    ä»»ä½ķä¸Ģ个
    -0.19
    鸱
    -0.19
    éĢļ讯åijĺ
    -0.19
     Circus
    -0.19
    å®ļçĤ¹
    -0.18
    éļ¾
    -0.18
    POSITIVE LOGITS
    -turned
    0.27
    æ²»
    0.22
     whose
    0.22
    åĩºèº«
    0.21
    å¨ĺ
    0.20
    åģ¶çĦ¶
    0.20
    çļĦ身份
    0.20
    -gallery
    0.20
    jÄĻ
    0.20
    opp
    0.19
    Activations Density 0.117%

    No Known Activations