© 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. 12450
    Prev
    Next
    INDEX
    Explanations

    horticultural or related fields

    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
    ãģªãĤīãģªãģĦ
    -0.19
    rior
    -0.19
    çģ«çĥ§
    -0.17
    FilterWhere
    -0.16
    /sl
    -0.16
    éĴĪ
    -0.16
    qli
    -0.16
     ÐłÐµÑģпÑĥб
    -0.16
    GuidId
    -0.16
    æ²³æµģåŁŁ
    -0.16
    POSITIVE LOGITS
    ment
    0.23
    ary
    0.19
    工夫
    0.18
    icultural
    0.18
    astr
    0.18
    ner
    0.17
     Dias
    0.17
    åĽŃ
    0.17
    gether
    0.17
    å¿ĥè¡Ģ
    0.17
    Activations Density 0.003%

    No Known Activations