© 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. 12660
    Prev
    Next
    INDEX
    Explanations

    suffix ending in "ting" or "ted"

    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
    -0.25
    halt
    -0.24
    ette
    -0.23
    holder
    -0.22
    hit
    -0.22
    rd
    -0.22
    hand
    -0.21
    host
    -0.21
    hay
    -0.21
    habit
    -0.20
    POSITIVE LOGITS
    ting
    0.56
    ted
    0.36
    TING
    0.34
    ypes
    0.34
    ters
    0.34
    ype
    0.33
    ãĤ¥
    0.32
    imes
    0.32
    tingham
    0.32
    tings
    0.31
    Activations Density 3.277%

    No Known Activations