© 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. 15774
    Prev
    Next
    INDEX
    Explanations

    specific dates and times

    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
     PaÅĦstwo
    -0.23
    à¸Ħà¸ĵะà¸ģรรม
    -0.22
    echa
    -0.21
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.21
    «
    -0.20
    æ¯ıæ¯ı
    -0.20
    æīįæĺ¯çľŁæŃ£
    -0.20
     unit
    -0.20
     ÐŁÐ¾Ñĩем
    -0.20
    èĥ½å¤Łåľ¨
    -0.19
    POSITIVE LOGITS
    æľĪåĪĿ
    0.19
    æħĿ
    0.18
    /native
    0.18
     fkk
    0.17
    ลา
    0.17
    人们对
    0.17
    .ToDateTime
    0.17
    unlock
    0.17
    _fm
    0.17
    伤çĹħ
    0.17
    Activations Density 0.007%

    No Known Activations