© 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. 12116
    Prev
    Next
    INDEX
    Explanations

    words ending in 'eople'

    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
    ãģıãĤĭ
    -0.28
    rd
    -0.20
    lf
    -0.19
    pop
    -0.19
    ously
    -0.19
    pack
    -0.18
    piece
    -0.18
    onne
    -0.17
    lt
    -0.17
    vation
    -0.17
    POSITIVE LOGITS
    ëĭĪëĭ¤
    0.33
    edia
    0.29
    erture
    0.27
    lication
    0.25
    ublish
    0.24
    pling
    0.24
    ulse
    0.24
    osition
    0.24
    refix
    0.23
    resent
    0.23
    Activations Density 1.768%

    No Known Activations