© 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. 10830
    Prev
    Next
    INDEX
    Explanations

    explorer and adventurer

    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
    eref
    -0.21
    çݯèĬĤ
    -0.20
    èŁł
    -0.19
    èĽ°
    -0.18
     içinde
    -0.18
    lsi
    -0.18
    ä¸Ĭè°ĥ
    -0.18
    ilter
    -0.18
    èݳ
    -0.18
    -checked
    -0.17
    POSITIVE LOGITS
    æİ¢éĻ©
    0.41
    æݢ索
    0.29
    åĨĴéĻ©
    0.25
    éĺŁéķ¿
    0.24
    åĭĺæİ¢
    0.23
     explorer
    0.23
     explor
    0.23
    åıijçİ°äºĨ
    0.22
    éĺŁåijĺ
    0.22
    äºļ马éĢĬ
    0.22
    Activations Density 0.036%

    No Known Activations