© 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. 11654
    Prev
    Next
    INDEX
    Explanations

    Jerry names

    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
    oes
    -0.21
    iate
    -0.20
    nement
    -0.17
    itud
    -0.17
    eds
    -0.17
    /her
    -0.16
    æĦıæĢĿ
    -0.16
    ally
    -0.16
    社ä¼ļåĮĸ
    -0.16
    åŃIJéĩĮ
    -0.16
    POSITIVE LOGITS
    town
    0.16
    ãģĩ
    0.15
    acob
    0.15
    ãĥĪãĥ«
    0.14
    çon
    0.14
     Ñģобой
    0.14
    å®ŀæĥł
    0.14
    说æĺ¯
    0.14
    åĬ¨çĶŁæĪIJ
    0.14
    yyyy
    0.14
    Activations Density 0.032%

    No Known Activations