© 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. 12083
    Prev
    Next
    INDEX
    Explanations

    and list separators

    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
    /Area
    -0.24
    ipur
    -0.21
     ÐŁÐ¾Ñĩем
    -0.20
    oning
    -0.20
    -like
    -0.19
     vet
    -0.19
    emen
    -0.19
     road
    -0.19
    ful
    -0.19
     f
    -0.19
    POSITIVE LOGITS
    æ·»åĬłåīĤ
    0.24
    第äºĮç§į
    0.22
    èľĤèľľ
    0.22
    å°ijéĩı
    0.22
    çļĦçĭ¬çī¹
    0.21
    ãģĤãģŁãĤĬ
    0.21
    éĻĦåĬł
    0.21
    å¸Ĥåľºä»½é¢Ŀ
    0.21
    å·®å¼ĤåĮĸ
    0.21
    çļĦåĬŁæķĪ
    0.21
    Activations Density 0.002%

    No Known Activations