© 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. 11663
    Prev
    Next
    INDEX
    Explanations

    mode selection

    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
    ness
    -0.19
    à¸ģา
    -0.19
    ree
    -0.18
    çĸĻ
    -0.17
    wort
    -0.17
    reate
    -0.16
    ONA
    -0.16
    umping
    -0.16
    äºĽ
    -0.16
    bane
    -0.15
    POSITIVE LOGITS
    ä¸ĭçļĦ
    0.21
    åŁ
    0.20
    æĢģ
    0.19
    ãĢħ
    0.19
    æħĭ
    0.19
    ï¸ı
    0.18
    åŃIJéĩĮ
    0.18
    æĥħæĻ¯
    0.16
    å®ļäºĨ
    0.16
     игÑĢÑĭ
    0.16
    Activations Density 0.028%

    No Known Activations