© 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. 13200
    Prev
    Next
    INDEX
    Explanations

    cre/gre word beginnings

    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
    ../
    -0.24
    yla
    -0.17
    ored
    -0.17
    room
    -0.16
    ãĥ³ãĤ°
    -0.16
    edral
    -0.16
    cake
    -0.16
    entication
    -0.16
    ically
    -0.16
    ãĤ¥
    -0.16
    POSITIVE LOGITS
    atively
    0.18
    ãģĨãģ¡ãģ«
    0.17
    说æĺ¯
    0.17
    è°Ľ
    0.16
    ATURE
    0.16
    åį«è§Ĩ
    0.16
    bble
    0.15
    ../../../
    0.15
    IGO
    0.15
    çĶŁèĤĸ
    0.15
    Activations Density 0.038%

    No Known Activations