© 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. 13674
    Prev
    Next
    INDEX
    Explanations

    fMRI brain imaging studies

    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
    numerusform
    -0.25
    CLUD
    -0.25
    mPid
    -0.24
     DropIndex
    -0.23
     PANEL
    -0.23
    oldt
    -0.22
    dge
    -0.22
    PropertyParams
    -0.22
    aeper
    -0.21
    ciÄħg
    -0.21
    POSITIVE LOGITS
    大èĦij
    0.34
    èĦij
    0.30
     brain
    0.30
    Brain
    0.26
    brain
    0.26
     voxel
    0.23
     imaging
    0.23
     mapping
    0.23
    çĤ¹äº®
    0.23
     maps
    0.22
    Activations Density 0.236%

    No Known Activations