© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15258
    Prev
    Next
    INDEX
    Explanations

    printing console output

    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
    reff
    -0.19
     Heck
    -0.19
    ValueHandling
    -0.19
     Bel
    -0.19
     Convers
    -0.19
    Alexander
    -0.19
    ungan
    -0.18
    .BackgroundImage
    -0.18
    versations
    -0.18
    eea
    -0.18
    POSITIVE LOGITS
     output
    0.39
    è¾ĵåĩº
    0.37
     Output
    0.35
    Output
    0.33
    output
    0.32
    _output
    0.29
    _OUTPUT
    0.29
     è¾ĵåĩº
    0.29
     display
    0.27
     outputs
    0.27
    Activations Density 0.470%

    No Known Activations