© 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. 12167
    Prev
    Next
    INDEX
    Explanations

    URLs containing numeric identifiers

    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
    arten
    -0.23
    ikan
    -0.22
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.20
    bed
    -0.20
    à¸Ħà¸ĵะà¸ģรรม
    -0.20
     à¹Ģมษ
    -0.20
    è¾ŀ
    -0.20
    iler
    -0.19
     à¸ŀฤษ
    -0.19
    ç´ł
    -0.19
    POSITIVE LOGITS
    åģ¥
    0.21
    è¾ĩ
    0.20
    _factors
    0.19
    -pages
    0.18
    orate
    0.18
    çĹī
    0.18
    太太
    0.17
     chaud
    0.17
    çģ°å°ĺ
    0.17
    é»Ħæĺı
    0.17
    Activations Density 0.067%

    No Known Activations