© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14971
    Prev
    Next
    INDEX
    Explanations

    years

    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
     kil
    -0.18
     DO
    -0.18
    éļıæīĭ
    -0.18
    ungle
    -0.18
     cli
    -0.18
    .POS
    -0.18
    stick
    -0.18
    bil
    -0.17
    -ms
    -0.17
    åĥı
    -0.17
    POSITIVE LOGITS
    ä¸ļ绩
    0.21
     Opr
    0.20
    Except
    0.20
    ä¸Ģè´¯
    0.20
    apos
    0.19
     Nicholson
    0.19
     Hilton
    0.19
    ALLY
    0.18
    åĭĥ
    0.18
    è¢į
    0.18
    Activations Density 0.018%

    No Known Activations