© 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. 14421
    Prev
    Next
    INDEX
    Explanations

    meteor and meteorological

    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
    å±Ĥ次
    -0.19
    OrCreate
    -0.18
    è¯ķ管
    -0.18
     eternity
    -0.16
    ëģĶ
    -0.16
    åŁºè°ĥ
    -0.16
    æł¼å°Ķ
    -0.15
    .deepcopy
    -0.15
    æĤ¦
    -0.15
    หมà¸Ķ
    -0.15
    POSITIVE LOGITS
    åŃ¦å®¶
    0.23
    ically
    0.21
    ally
    0.21
    ized
    0.21
    à¹Į
    0.20
    ización
    0.20
    ological
    0.20
    son
    0.19
    ization
    0.19
    ship
    0.19
    Activations Density 0.005%

    No Known Activations