© 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. 13606
    Prev
    Next
    INDEX
    Explanations

    score or scored

    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
    æĭħè´Ł
    -0.20
    ÑĢок
    -0.19
    omic
    -0.18
    çľģéĴ±
    -0.18
    æı´åĬ©
    -0.18
    ä½ĵ积
    -0.18
    以人为
    -0.18
     ÐłÐ°Ð·Ð¼ÐµÑĢ
    -0.18
     hops
    -0.18
    åħĪè¿ĽæĬĢæľ¯
    -0.18
    POSITIVE LOGITS
     score
    0.45
    å¾ĹåĪĨ
    0.44
    åĪĨæķ°
    0.40
    score
    0.39
     scores
    0.37
    .score
    0.36
    Score
    0.35
    	score
    0.35
    è¯ĦåĪĨ
    0.33
     scored
    0.33
    Activations Density 0.061%

    No Known Activations