© 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. 13378
    Prev
    Next
    INDEX
    Explanations

    hydroxyl or hydroxide compounds

    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
     lắm
    -0.18
    isman
    -0.17
    SSION
    -0.17
    åĴĮåľ°åĮº
    -0.17
    colm
    -0.16
    rijk
    -0.16
    ä¸įéĢļ
    -0.16
    loor
    -0.16
    误导
    -0.16
    ties
    -0.16
    POSITIVE LOGITS
    人æµģ
    0.22
    ä»Ģä¹ĪæŶåĢĻ
    0.18
    åĹŁ
    0.18
    æĹĥ
    0.17
    lik
    0.17
    Uber
    0.17
     Ngô
    0.17
    estre
    0.16
    人类
    0.16
    oint
    0.16
    Activations Density 0.022%

    No Known Activations