© 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. 15625
    Prev
    Next
    INDEX
    Explanations

    casting or cast

    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
    媳
    -0.20
    екÑĤоÑĢ
    -0.16
    ÑĪе
    -0.16
    ymous
    -0.16
    и
    -0.16
    å²Ķ
    -0.16
    ector
    -0.15
    -même
    -0.15
    erator
    -0.15
    å®ŀæĥł
    -0.15
    POSITIVE LOGITS
    aways
    0.23
    ling
    0.23
    ings
    0.22
    ers
    0.21
    igated
    0.21
    backs
    0.19
    ed
    0.19
    ively
    0.18
    away
    0.18
     aside
    0.18
    Activations Density 0.025%

    No Known Activations