© 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. 13677
    Prev
    Next
    INDEX
    Explanations

    at least

    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
    å°¤åħ¶æĺ¯
    -0.23
    å°¤åħ¶
    -0.22
    çī¹åĪ«æĺ¯
    -0.20
     PARTICULAR
    -0.20
     especially
    -0.20
    especially
    -0.18
    çıħ
    -0.18
    igan
    -0.18
    ë°
    -0.18
    åIJ¬åıĸ
    -0.18
    POSITIVE LOGITS
    åĨħ涵
    0.20
    äºİæѤ
    0.20
    heits
    0.20
    prs
    0.19
    ModelProperty
    0.19
    -indent
    0.18
    urers
    0.18
    oppers
    0.17
    ulant
    0.17
    uristic
    0.17
    Activations Density 0.038%

    No Known Activations