© 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. 13828
    Prev
    Next
    INDEX
    Explanations

    list iterators and lengths

    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
    è¡Ķ
    -0.21
    ordes
    -0.21
    æĿĸ
    -0.19
    icens
    -0.19
    赫
    -0.19
     Marl
    -0.19
    ior
    -0.19
    MULT
    -0.19
    æĦıè¯Ĩ
    -0.18
    _href
    -0.18
    POSITIVE LOGITS
     vex
    0.21
     Åŀe
    0.21
    ä¾Ľå¤§å®¶
    0.19
    IDGET
    0.18
     внеÑĪне
    0.18
    çĥ¦
    0.18
    åı¦æľī
    0.17
     Câm
    0.17
    çİĺ
    0.17
    ãĤĴå¤īãģĪ
    0.17
    Activations Density 0.876%

    No Known Activations