© 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. 12642
    Prev
    Next
    INDEX
    Explanations

    congenital

    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
    tail
    -0.20
    åĺ´
    -0.19
    ย
    -0.18
    çİ°çĬ¶
    -0.18
    å°¾
    -0.18
    çİ°è¡Į
    -0.18
    orce
    -0.17
    atum
    -0.17
    etz
    -0.17
    GLOBALS
    -0.17
    POSITIVE LOGITS
    æĢ§
    0.20
    /static
    0.19
    /basic
    0.19
    اتÙĩÙħ
    0.18
    æĢ§çļĦ
    0.18
    æĢ§åĴĮ
    0.18
    mente
    0.18
    .unknown
    0.17
    ventions
    0.17
    çĶ¨åĵģ
    0.16
    Activations Density 0.035%

    No Known Activations