© 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. 11274
    Prev
    Next
    INDEX
    Explanations

    respectively

    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
    actable
    -0.20
    ÑĭÑĤа
    -0.20
    abbo
    -0.20
    çĮĹ
    -0.20
    尤为
    -0.19
    åŁĴ
    -0.19
    .lex
    -0.19
    åĽłä¸ºå®ĥ
    -0.19
    rex
    -0.18
     Merrill
    -0.18
    POSITIVE LOGITS
     respectively
    0.40
    åIJĦèĩªçļĦ
    0.36
    åIJĦèĩª
    0.35
     respective
    0.33
    åĪĨåĪ«
    0.32
    ãģĿãĤĮãģŀãĤĮ
    0.32
    åīįèĢħ
    0.32
    åĪĨåĪ«ä¸º
    0.31
    åĪĨåĪ«æĺ¯
    0.30
    åIJĦæľī
    0.27
    Activations Density 0.482%

    No Known Activations