© 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. 16833
    Prev
    Next
    INDEX
    Explanations

    U.S. Attorney

    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
    ĥģ
    -0.21
    èĥ½å¾ĹåĪ°
    -0.21
     pros
    -0.19
    èĭ«
    -0.19
     ministries
    -0.18
    atory
    -0.18
    èĢģ人家
    -0.18
    çݯåį«
    -0.18
    inish
    -0.18
    yr
    -0.18
    POSITIVE LOGITS
    éĿ´
    0.24
    åįĹæĸ¹
    0.19
     ErrorMessage
    0.19
    ights
    0.19
    å»Ĭ
    0.19
    (grad
    0.19
     roman
    0.18
     roma
    0.18
    aub
    0.18
     Cath
    0.18
    Activations Density 0.019%

    No Known Activations