© 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. 11940
    Prev
    Next
    INDEX
    Explanations

    doing activities

    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
    imed
    -0.20
    imo
    -0.20
    举åĬ¨
    -0.19
    AYS
    -0.18
     Conte
    -0.17
    鼶
    -0.17
    ForKey
    -0.17
    dux
    -0.17
    AGMA
    -0.16
     upfront
    -0.16
    POSITIVE LOGITS
    鹬
    0.19
    ç¾İ好çĶŁæ´»
    0.18
    еÑĩ
    0.18
    ramids
    0.18
    æ¯ıä¸Ģä½į
    0.18
    åįĹæĸ¹
    0.17
    çľĭä¸įè§ģ
    0.17
     Sitting
    0.17
     alph
    0.17
     Gol
    0.17
    Activations Density 0.106%

    No Known Activations