© 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. 16219
    Prev
    Next
    INDEX
    Explanations

    DISTRICT OF

    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
    å¾Ī
    -0.20
     sim
    -0.20
     chances
    -0.20
    ä¼¼
    -0.19
    à¹Ĩ
    -0.19
    .EN
    -0.19
    çĶļ
    -0.18
     chance
    -0.18
     same
    -0.18
    sim
    -0.17
    POSITIVE LOGITS
    çģ«çĤ¬
    0.20
    审计
    0.19
    ç»
    0.19
    ToLocal
    0.19
    aira
    0.19
    缴å±ŀ
    0.19
     Affero
    0.18
    çĿ£åĬŀ
    0.18
    /licenses
    0.18
    åīįéĢĶ
    0.18
    Activations Density 0.062%

    No Known Activations