© 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. 13897
    Prev
    Next
    INDEX
    Explanations

    references and citations

    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
    CESS
    -0.23
    esser
    -0.21
    inte
    -0.20
    adin
    -0.20
    ç©¿æĪ´
    -0.19
    äºĨä»ĸçļĦ
    -0.19
     Cave
    -0.18
    inté
    -0.18
     Loads
    -0.18
    å§Ķ
    -0.18
    POSITIVE LOGITS
    ä¸įåĩº
    0.21
     nostr
    0.21
    åģļä¸įåĪ°
    0.21
    æ¹Ħ
    0.19
    èĥ¸åı£
    0.19
     airst
    0.18
    åĪĨæīĭ
    0.18
    çļĦ人éĥ½
    0.18
    arshal
    0.17
    lemen
    0.17
    Activations Density 0.004%

    No Known Activations