© 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. 14768
    Prev
    Next
    INDEX
    Explanations

    mystery Benedict Secret Box film London

    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
     thá»Ń
    -0.19
    manship
    -0.17
    æŃ£å¸¸ä½¿çĶ¨
    -0.17
    åļı
    -0.17
    uated
    -0.16
    æĦıè§ģ
    -0.16
     Äijỡ
    -0.16
    åħ¬å®īå±Ģ
    -0.16
    SON
    -0.16
    bury
    -0.16
    POSITIVE LOGITS
    åħ®
    0.22
    rd
    0.20
    naire
    0.19
    éĩįéĩį
    0.19
     minded
    0.19
    té
    0.18
    ariat
    0.18
    ously
    0.18
    vale
    0.17
    -minded
    0.17
    Activations Density 0.010%

    No Known Activations