© 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. 13080
    Prev
    Next
    INDEX
    Explanations

    of their

    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
    à¸Ħà¸ĵะà¸ģรรม
    -0.27
     à¹Ģมษ
    -0.26
     à¸ŀฤษ
    -0.25
     Derne
    -0.25
     Detaylı
    -0.25
    à¹Ģà¸Ĺศà¸ģา
    -0.25
    è´°
    -0.25
     Câm
    -0.24
     มà¸ģร
    -0.24
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.24
    POSITIVE LOGITS
     spep
    0.25
    ãĢĬ
    0.25
    ¡´
    0.23
     danmark
    0.23
     strapon
    0.22
     shemale
    0.22
     milfs
    0.22
     taxp
    0.22
     miÄĻdz
    0.22
    ê»Ħ
    0.22
    Activations Density 0.268%

    No Known Activations