© 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. 11112
    Prev
    Next
    INDEX
    Explanations

    open source projects

    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
    ChartData
    -0.20
    rase
    -0.20
    ouve
    -0.20
    arna
    -0.19
    oral
    -0.19
    olly
    -0.18
    rens
    -0.17
    ren
    -0.17
    cestor
    -0.17
    è°Ģ
    -0.17
    POSITIVE LOGITS
    ä¼Ĺ
    0.21
    -minded
    0.21
     minded
    0.21
    åĮĸçļĦ
    0.17
    iert
    0.16
    manship
    0.16
    iquer
    0.16
    wers
    0.16
    ellation
    0.16
    人士
    0.16
    Activations Density 0.012%

    No Known Activations