© 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. 13329
    Prev
    Next
    INDEX
    Explanations

    suddenly followed by an event

    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
    缮åīįå·²ç»ı
    -0.20
    éļıåIJİ
    -0.19
    å½ĵæŶçļĦ
    -0.18
    orts
    -0.18
    enz
    -0.18
    åĨħçļĦ
    -0.18
    à¹Ħà¸Ĺย
    -0.18
    utex
    -0.17
    å¸ĥæľĹ
    -0.17
    éĵ¢
    -0.17
    POSITIVE LOGITS
    aneously
    0.30
    aneous
    0.22
    izer
    0.21
    tion
    0.20
    ness
    0.18
     forth
    0.18
    置身
    0.18
    ity
    0.18
    æĥ³èµ·
    0.17
    ibil
    0.17
    Activations Density 0.009%

    No Known Activations