© 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. 16883
    Prev
    Next
    INDEX
    Explanations

    JJ .J ., packages will

    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
    称ä¹ĭ为
    -0.20
    éĹ¨æ§Ľ
    -0.20
    OMEM
    -0.19
    建çŃijå·¥ç¨ĭ
    -0.18
     Johns
    -0.18
    _RECT
    -0.18
    å°ıçĻ½
    -0.18
    æ±°
    -0.18
    claimer
    -0.18
    çijĽ
    -0.18
    POSITIVE LOGITS
    é¾Į
    0.20
    èĩ´æķ¬
    0.20
     likes
    0.19
     subs
    0.18
    .metro
    0.18
    å¤ļåIJį
    0.18
    为äºĨéģ¿åħį
    0.18
    ç³Ĺ
    0.18
    æĻĭ级
    0.18
    adm
    0.18
    Activations Density 0.001%

    No Known Activations