© 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. 14993
    Prev
    Next
    INDEX
    Explanations

    new version or update

    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
    éĺĨ
    -0.20
    åįµ
    -0.19
     Thứ
    -0.19
    污æŁĵéĺ²æ²»
    -0.19
    ANGO
    -0.19
    ilha
    -0.19
    akov
    -0.18
    isible
    -0.18
    xDE
    -0.18
    Invoke
    -0.17
    POSITIVE LOGITS
    çīĪæľ¬
    0.29
    ä¼łç»ŁçļĦ
    0.29
     version
    0.29
    version
    0.27
    çīĪ
    0.26
    ç»ıåħ¸çļĦ
    0.25
     versions
    0.24
    -version
    0.22
    äºĨä¸Ģä¸ĭ
    0.22
     Cort
    0.22
    Activations Density 0.037%

    No Known Activations