© 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. 13700
    Prev
    Next
    INDEX
    Explanations

    men's

    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
    mente
    -0.20
    OrUpdate
    -0.19
    ../../../
    -0.18
    ses
    -0.18
    ä»Ģä¹ĪåİŁåĽł
    -0.17
    Ñĩик
    -0.16
    sWith
    -0.16
    ly
    -0.16
    ا
    -0.15
    undi
    -0.15
    POSITIVE LOGITS
    esis
    0.21
    endez
    0.21
    vironment
    0.20
    ial
    0.20
    est
    0.19
    perature
    0.17
    ÑģÑĤÑĮ
    0.17
    opause
    0.17
    folk
    0.17
    igma
    0.16
    Activations Density 0.034%

    No Known Activations