© 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. 14389
    Prev
    Next
    INDEX
    Explanations

    Matrix, The, Impact, Ru, Favorite

    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
    ä¸Ģ对
    -0.23
    kie
    -0.20
     UNUSED
    -0.20
     اÙĦÙĥرÙĬÙħ
    -0.19
    èģĶæĥ³
    -0.19
     ker
    -0.19
     opener
    -0.19
     kê
    -0.18
    é¾Ħ
    -0.18
    çĦ¦
    -0.18
    POSITIVE LOGITS
    Elim
    0.23
    åħīå½±
    0.23
    tras
    0.22
    éĨĴæĿ¥
    0.21
     reality
    0.21
    鸡汤
    0.21
     virtual
    0.21
    æݧåĪ¶ç³»ç»Ł
    0.21
    è¿Ļ个ä¸ĸçķĮ
    0.20
    virtual
    0.20
    Activations Density 0.021%

    No Known Activations