© 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. 15071
    Prev
    Next
    INDEX
    Explanations

    closures or access restrictions

    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
    åľ¨åħ¨åĽ½
    -0.22
    åĺ´éĩĮ
    -0.21
    é¾ĥ
    -0.21
    çĤ¹äº®
    -0.20
    sav
    -0.19
    奴
    -0.18
    丰åİļ
    -0.18
     unsub
    -0.18
    é«ĺåİŁ
    -0.17
    (Data
    -0.17
    POSITIVE LOGITS
    æİī
    0.22
    æŀ¶
    0.21
    举
    0.20
    isse
    0.19
    éĹŃ
    0.19
     scissors
    0.19
    lesia
    0.19
    usu
    0.18
    isha
    0.18
    举åįĹ
    0.18
    Activations Density 0.014%

    No Known Activations