© 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. 13359
    Prev
    Next
    INDEX
    Explanations

    feast

    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
    çĿ¬
    -0.20
    ãĥ¼ãĥł
    -0.18
    失误
    -0.18
    ãģĦãĤĭ
    -0.17
    ÑĪен
    -0.17
    ippo
    -0.17
    è§īå¾Ĺå¾Ī
    -0.16
    erb
    -0.16
    ï¸ı
    -0.16
    æį©
    -0.16
    POSITIVE LOGITS
    åĨħ容
    0.23
    ful
    0.22
    ings
    0.22
    pole
    0.22
    ivals
    0.20
    è¿ĩåIJİ
    0.17
    fully
    0.17
    çļĦåĨħ容
    0.17
     hall
    0.17
    ¾
    0.17
    Activations Density 0.002%

    No Known Activations