© 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. 11942
    Prev
    Next
    INDEX
    Explanations

    day, anniversary, Q, Con

    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
     ÑħозÑıйÑģÑĤв
    -0.21
    ibi
    -0.20
    ãģ¾ãģķ
    -0.20
    鸥
    -0.20
    çijĢ
    -0.20
    èĢĥ
    -0.19
     penc
    -0.19
    æıĸ
    -0.18
    ç¦
    -0.18
     epub
    -0.18
    POSITIVE LOGITS
    èģĶåIJĪåĽ½
    0.20
    ammen
    0.20
    istic
    0.19
    轸
    0.18
    å®īå®ļ
    0.17
    Å»
    0.17
     Plat
    0.17
    .tm
    0.17
    vertising
    0.17
    æ¼Ķ讲
    0.17
    Activations Density 0.009%

    No Known Activations