© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15212
    Prev
    Next
    INDEX
    Explanations

    daylight length, time, periods

    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
    DateFormat
    -0.19
    涴
    -0.19
    keh
    -0.19
    ez
    -0.18
    ikk
    -0.18
    åħ³éĶ®è¯į
    -0.18
    ç¨Ģ缺
    -0.18
     pa
    -0.17
     Blow
    -0.17
     prime
    -0.17
    POSITIVE LOGITS
    æľŁéĹ´
    0.24
    è®®æ¡Ī
    0.22
    èĿĩ
    0.21
     periods
    0.21
    ynchronization
    0.20
    uin
    0.20
    VML
    0.20
    åĥįãģı
    0.19
    éĢģ
    0.19
     vard
    0.19
    Activations Density 0.001%

    No Known Activations