© 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. 13087
    Prev
    Next
    INDEX
    Explanations

    Bruce [surname/initial]

    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
    tures
    -0.23
    ths
    -0.21
    slashes
    -0.19
    ../../../
    -0.19
    reas
    -0.18
    èļ§
    -0.18
    ting
    -0.18
    åŃIJéĩĮ
    -0.18
    Ùĥ
    -0.17
    ÑĢиÑģÑĤ
    -0.17
    POSITIVE LOGITS
    ãģĹãģ¾ãģĦ
    0.18
    sdale
    0.15
     Ches
    0.15
     erection
    0.15
    hood
    0.15
    %%%%
    0.14
    hift
    0.14
    vale
    0.14
     unveiling
    0.14
    æ®Ĩ
    0.14
    Activations Density 0.005%

    No Known Activations