© 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. 15723
    Prev
    Next
    INDEX
    Explanations

    dimensions like 16x20, 10x10, 80:20, 4- 2x4s, 2ÃĹ2, 7x5

    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
    cke
    -0.23
    intree
    -0.19
    ç»ıèIJ¥
    -0.19
    å¤ľéĩĮ
    -0.19
     Bros
    -0.18
    æľ¦èĥ§
    -0.18
    -anchor
    -0.17
     Zuk
    -0.17
    ç»ŀ
    -0.17
    hub
    -0.17
    POSITIVE LOGITS
    meld
    0.22
    pathname
    0.20
    éĵº
    0.19
    æ¥ŀ
    0.19
    _Handle
    0.19
    åİ¢
    0.19
    HSV
    0.19
    çĥ«
    0.18
    docs
    0.18
    建åĨĽ
    0.18
    Activations Density 0.001%

    No Known Activations