© 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. 12179
    Prev
    Next
    INDEX
    Explanations

    ideology or IDE

    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
    iples
    -0.19
    à¹Ĩ
    -0.19
    èįª
    -0.18
    ãĤĪãģĨãģª
    -0.18
    iple
    -0.18
    /rem
    -0.17
    woods
    -0.17
    ../
    -0.16
    stick
    -0.16
    orate
    -0.16
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.25
    åĴĮ社ä¼ļ
    0.20
    ic
    0.19
    ician
    0.19
    ically
    0.18
    angelo
    0.18
    иÑĢован
    0.17
    yll
    0.16
    ä»Ĺ
    0.16
    lect
    0.16
    Activations Density 0.005%

    No Known Activations