© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17007
    Prev
    Next
    INDEX
    Explanations

    the shows The Monitor, The Morning

    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¸Ģéģĵ
    -0.19
    ams
    -0.19
    éĶ¦ç»£
    -0.18
    åIJĮäºĭ们
    -0.18
    ä¸ĢåĿĹ
    -0.17
    éłĨ
    -0.17
    缸åħ³äººåijĺ
    -0.17
    çļĦä¸ĢéĿ¢
    -0.17
    ·»
    -0.17
    æ¯Ļ
    -0.17
    POSITIVE LOGITS
    ArrayOf
    0.20
    FilterWhere
    0.19
    matchCondition
    0.18
    	RTLR
    0.18
    isser
    0.17
    ruc
    0.17
    $fdata
    0.17
    iscrim
    0.17
    numerusform
    0.17
    "urls
    0.16
    Activations Density 0.209%

    No Known Activations