© 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. 13170
    Prev
    Next
    INDEX
    Explanations

    titration, addition, evaporation

    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
    çŁŃæľŁ
    -0.20
    æĪĴ
    -0.20
    æĪĸå¤ļ
    -0.19
    æĵ¦
    -0.19
    FLT
    -0.19
     LIS
    -0.19
    éĺľ
    -0.19
    éªĮ
    -0.18
    olis
    -0.18
    çĶļèĩ³æĺ¯
    -0.18
    POSITIVE LOGITS
    éĢIJä¸Ģ
    0.22
    aqu
    0.18
    Inv
    0.18
     наÑĪ
    0.18
     Alejandro
    0.18
     Associ
    0.17
    .Inv
    0.17
    евÑĭÑħ
    0.17
    稳æŃ¥æİ¨è¿Ľ
    0.17
     Weiner
    0.17
    Activations Density 0.010%

    No Known Activations