© 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. 14639
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location or direction

    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
    ç¿İ
    -0.21
    FilterWhere
    -0.21
    á»ĵng
    -0.20
    atedRoute
    -0.20
    åĢ«
    -0.19
    åĻ¨å®ĺ
    -0.19
    说çļĦæĺ¯
    -0.18
    zÄĻ
    -0.18
    .padding
    -0.18
    oyal
    -0.18
    POSITIVE LOGITS
    并ä¸İ
    0.20
    åħ¨åľº
    0.20
    ALL
    0.20
    demo
    0.19
    訾
    0.19
    flush
    0.18
    begin
    0.18
    aise
    0.18
    家人
    0.18
    åħ¨ãģ¦
    0.18
    Activations Density 0.006%

    No Known Activations