© 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. 13144
    Prev
    Next
    INDEX
    Explanations

    Tiger Woods

    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
    sst
    -0.21
    sWith
    -0.21
    sel
    -0.19
    sis
    -0.19
    sq
    -0.19
    ãģŁãĤģãģ«
    -0.19
    sd
    -0.19
    sn
    -0.19
    sr
    -0.19
    yer
    -0.18
    POSITIVE LOGITS
    lijk
    0.18
    áĢĦ
    0.17
    thumbs
    0.17
    æį®ç»Łè®¡
    0.17
    hood
    0.16
    rights
    0.16
    etty
    0.16
    bero
    0.16
    IVATE
    0.15
    çĶŁçĶŁ
    0.15
    Activations Density 0.005%

    No Known Activations