© 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. 11766
    Prev
    Next
    INDEX
    Explanations

    research paper, story, insurance, department, divorce

    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
    atoms
    -0.18
    sut
    -0.18
    aines
    -0.17
     emb
    -0.17
    eln
    -0.17
    emb
    -0.17
    clipse
    -0.17
     buckle
    -0.17
    穹
    -0.16
    qm
    -0.16
    POSITIVE LOGITS
    类似çļĦ
    0.21
    åIJĮæł·çļĦ
    0.20
    åİŁæĸĻ
    0.20
    åĽ½æ°ij
    0.19
    losed
    0.18
    寿åij½
    0.18
    级以ä¸Ĭ
    0.18
    èĢģé¼ł
    0.17
    客æĪ·éľĢæ±Ĥ
    0.17
    平淡
    0.17
    Activations Density 0.090%

    No Known Activations