© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14922
    Prev
    Next
    INDEX
    Explanations

    home or service

    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
    æĬ«éľ²
    -0.20
    agg
    -0.20
    åħ¬çĦ¶
    -0.20
    åIJ¯èĴĻ
    -0.20
    ä¸įæĥľ
    -0.19
    Ear
    -0.19
    ä¸įåľ¨ä¹İ
    -0.19
    åıijå±ķä¸Ń
    -0.19
    ages
    -0.18
    ubi
    -0.18
    POSITIVE LOGITS
    ä¸įåĩº
    0.30
    ä¸įåĬ¨
    0.30
    åĿIJåľ¨
    0.29
    躺çĿĢ
    0.27
    åĿIJçĿĢ
    0.26
    èººåľ¨åºĬä¸Ĭ
    0.25
    åľ¨å®¶
    0.24
     passive
    0.24
    åľ¨å®¶éĩĮ
    0.24
    åĿIJ
    0.23
    Activations Density 0.214%

    No Known Activations