© 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. 11201
    Prev
    Next
    INDEX
    Explanations

    code definition and links

    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
    æ´»
    -0.30
    家
    -0.26
    åħ¶
    -0.26
    i
    -0.26
    被
    -0.26
    l
    -0.25
    åIJĮ
    -0.25
    m
    -0.24
    y
    -0.24
     serv
    -0.23
    POSITIVE LOGITS
    _ComCallableWrapper
    0.24
    atform
    0.23
    ',['../
    0.22
    æľĥåĵ¡è¨»åĨĬ
    0.22
     taxp
    0.22
    обоÑĢоÑĤ
    0.22
    é¬ĵ
    0.22
     addCriterion
    0.21
    æī«é»ijéĻ¤
    0.21
    _derivative
    0.21
    Activations Density 0.002%

    No Known Activations