© 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. 13719
    Prev
    Next
    INDEX
    Explanations

    Windows version numbers

    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
    flix
    -0.20
     usur
    -0.19
    iot
    -0.19
    巨人
    -0.19
     ÐIJлекÑģан
    -0.19
     Salisbury
    -0.19
    æŶåĪ»
    -0.19
    ount
    -0.19
    nom
    -0.18
    ou
    -0.18
    POSITIVE LOGITS
    à¹ĥà¸Ķ
    0.22
    å²ģ以ä¸ĭ
    0.21
    çĻ¾å¹´
    0.20
    åıĭ好
    0.20
    åĽłåľ°
    0.20
     Compatibility
    0.20
    èĢģé¾Ħ
    0.19
    å¼ķçĪĨ
    0.19
    骨头
    0.19
    æľĢä½İ
    0.19
    Activations Density 0.071%

    No Known Activations