© 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. 12622
    Prev
    Next
    INDEX
    Explanations

    negative connotations, scandals, or bad events

    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
    æľīäºĽ
    -0.21
    -ish
    -0.20
    渴
    -0.19
    æľīä¸Ģå®ļçļĦ
    -0.19
     thirst
    -0.19
    Sortable
    -0.19
     Hayward
    -0.18
    çķ¥æľī
    -0.18
    -like
    -0.18
    èĪ¬çļĦ
    -0.18
    POSITIVE LOGITS
    ãģ©ãģĵãĤį
    0.25
    äd
    0.21
    èĤĮèĤ¤
    0.19
    анÑĤ
    0.19
    ÑĦа
    0.19
    ç¡®åĪĩ
    0.19
    amy
    0.18
    ç»Īæŀģ
    0.18
    æŀģ度
    0.18
    æŀģåħ¶
    0.18
    Activations Density 0.497%

    No Known Activations