© 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. 11933
    Prev
    Next
    INDEX
    Explanations

    lets say / let us say

    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
    mani
    -0.19
    æĶ¹å»º
    -0.19
    ible
    -0.18
     themselves
    -0.18
    rea
    -0.18
    ograd
    -0.17
    ará
    -0.17
    owed
    -0.17
    è£Ķ
    -0.17
     likely
    -0.17
    POSITIVE LOGITS
     hypoth
    0.30
    åIJ§
    0.28
    ä½łæĥ³
    0.26
    ä½łåľ¨
    0.26
    åģĩ设
    0.23
    ä½łæĺ¯
    0.23
     hypothetical
    0.22
    ä½ł
    0.21
    ecz
    0.21
    æĥħå¢ĥ
    0.20
    Activations Density 0.098%

    No Known Activations