© 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. 15220
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations and titles

    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
     particular
    -0.23
    -l
    -0.21
     uniform
    -0.21
    t
    -0.20
     specific
    -0.20
    çļĦåIJĦç§į
    -0.20
    ken
    -0.20
     lot
    -0.20
    ...
    -0.20
    bl
    -0.20
    POSITIVE LOGITS
    .debugLine
    0.26
     spep
    0.25
     taxp
    0.24
    ernetes
    0.23
    ERSHEY
    0.22
     knull
    0.22
     backpage
    0.22
     uLocal
    0.22
    å¢ħ
    0.22
     sourceMapping
    0.21
    Activations Density 0.064%

    No Known Activations