© 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. 13731
    Prev
    Next
    INDEX
    Explanations

    scheduling and timing

    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
    çĸĻ
    -0.21
     Ñģвоими
    -0.21
    ÑĢак
    -0.20
    æľīèī²
    -0.20
    èĽī
    -0.20
    ãĤŃãĥ¥
    -0.19
     COP
    -0.19
     wrought
    -0.19
    коп
    -0.19
    æ¶Ĥå±Ĥ
    -0.19
    POSITIVE LOGITS
    å®īæİĴ
    0.38
     schedule
    0.30
    ç´§åĩij
    0.29
     пÑĢиÑıÑĤн
    0.29
    çģµæ´»æĢ§
    0.26
    schedule
    0.26
     schedules
    0.25
    .schedule
    0.25
    çģµæ´»
    0.24
    åıĸæ¶Ī
    0.24
    Activations Density 0.056%

    No Known Activations