© 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. 16460
    Prev
    Next
    INDEX
    Explanations

    cross- prefix

    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
    atically
    -0.21
    stration
    -0.17
    iale
    -0.16
    zimmer
    -0.15
    opsy
    -0.15
    irst
    -0.15
    ush
    -0.15
    adier
    -0.15
    ORIZATION
    -0.15
    å°ıäºĭ
    -0.15
    POSITIVE LOGITS
    ings
    0.24
    ed
    0.22
    ingly
    0.21
    es
    0.21
    roads
    0.21
    most
    0.19
    bred
    0.19
    ible
    0.19
    妣
    0.19
    er
    0.19
    Activations Density 0.032%

    No Known Activations