© 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. 12517
    Prev
    Next
    INDEX
    Explanations

    offerings ending in ings

    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
    ural
    -0.19
     Ñģобой
    -0.19
    s
    -0.18
    ãģĤãģĴ
    -0.18
    ìłģìĿ´
    -0.17
    åĪĨå·¥
    -0.17
    ically
    -0.17
    ÙĬÙĥ
    -0.17
    ively
    -0.17
    enary
    -0.17
    POSITIVE LOGITS
    ings
    0.26
    INGS
    0.25
    sss
    0.20
    ss
    0.20
    enuity
    0.18
    amble
    0.18
    nin
    0.17
    tings
    0.17
    èĢħçļĦ
    0.17
    ä¸İåıijå±ķ
    0.17
    Activations Density 0.109%

    No Known Activations