© 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. 12673
    Prev
    Next
    INDEX
    Explanations

    programming code and identifiers

    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
    ä¸ĢæĹ¥
    -0.22
    ä¸ĢæŶ
    -0.21
    追
    -0.20
     Brush
    -0.19
    åĪ·
    -0.19
    åĬĽéĩı
    -0.19
    ubi
    -0.18
    æĿµ
    -0.18
    æĺ§
    -0.18
    ä¸Ģæł·
    -0.18
    POSITIVE LOGITS
     Cliff
    0.20
    çĹħæĥħ
    0.18
    ëĭ´
    0.18
    å§Ĵ
    0.18
    çī¹åĪ«æĺ¯åľ¨
    0.18
     Kle
    0.17
    subclass
    0.17
    kest
    0.17
    è··
    0.17
    -sizing
    0.17
    Activations Density 0.054%

    No Known Activations