© 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. 12893
    Prev
    Next
    INDEX
    Explanations

    california, calculus, calendars

    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
    elves
    -0.21
    lish
    -0.17
    ial
    -0.17
    eger
    -0.16
    ÑģÑĤи
    -0.16
    indle
    -0.15
    åĴIJ
    -0.15
    egral
    -0.15
    ego
    -0.15
    esis
    -0.15
    POSITIVE LOGITS
    culated
    0.21
    ifornia
    0.21
    éĵĽ
    0.19
    ibrate
    0.19
    culus
    0.18
    endars
    0.18
    ibrated
    0.18
    ibrator
    0.18
    iph
    0.17
    isations
    0.17
    Activations Density 0.033%

    No Known Activations