© 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. 14680
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations or acronyms

    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
    ek
    -0.23
    esse
    -0.23
    eker
    -0.22
    eb
    -0.21
    ems
    -0.21
    ev
    -0.21
    ef
    -0.21
    ehr
    -0.21
    ey
    -0.20
    иÑĢа
    -0.20
    POSITIVE LOGITS
    itional
    0.23
    hythm
    0.23
    side
    0.22
    outines
    0.21
    ée
    0.20
    aptor
    0.19
    HING
    0.19
    ities
    0.18
    iginal
    0.18
    anks
    0.18
    Activations Density 0.513%

    No Known Activations