© 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. 14530
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases

    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
    ç®į
    -0.18
    blr
    -0.18
     buc
    -0.17
    èĥ´
    -0.17
    rib
    -0.17
    azole
    -0.17
    æŀ§
    -0.17
     ÑħоÑĩ
    -0.17
    aze
    -0.17
    ä½łå¥½
    -0.17
    POSITIVE LOGITS
    æĥħåĨµè¿Ľè¡Į
    0.24
    éĥ¨åĪĨåľ°åĮº
    0.23
    æĸ¹å¼ıè¿Ľè¡Į
    0.22
    æľīåĬ©
    0.21
    åı¯çĸij
    0.20
    满æĦıçļĦ
    0.20
    éªĮ
    0.20
    注éĶĢ
    0.20
    举æĬ¥
    0.19
    è¾ħåĬ©
    0.19
    Activations Density 0.310%

    No Known Activations