© 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. 11234
    Prev
    Next
    INDEX
    Explanations

    listings and descriptions

    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
    acomment
    -0.19
     embod
    -0.19
    å´Ł
    -0.18
    استÙĤÙĦ
    -0.18
     Komment
    -0.18
    ByPrimaryKey
    -0.18
    @email
    -0.18
     اÙĦجÙħÙĩ
    -0.18
    Ø£Ùĩد
    -0.18
    Ø¥ÙĨØ´
    -0.18
    POSITIVE LOGITS
     related
    0.23
    åĢ¾åIJij
    0.23
    缸åħ³çļĦ
    0.23
    缸åħ³
    0.23
    çĻ¾ç§ij
    0.21
    缸åħ³åĨħ容
    0.20
    çľ¼ä¸ĭ
    0.20
    è¯Ŀé¢ĺ
    0.20
    åĩºå¤Ħ
    0.19
    PERT
    0.19
    Activations Density 0.031%

    No Known Activations