© 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. 10754
    Prev
    Next
    INDEX
    Explanations

    job takers/makers/painters

    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
    äºĮåŃĹ
    -0.21
    建设çĶ¨åľ°
    -0.21
    ry
    -0.20
    ship
    -0.19
    iert
    -0.19
    ogram
    -0.18
    bere
    -0.18
    åĴĮ社ä¼ļ
    -0.18
    èĪ¬çļĦ
    -0.17
    å´ģ
    -0.17
    POSITIVE LOGITS
    -upper
    0.23
    ç¨Ģ
    0.21
    -out
    0.19
    ÑģÑı
    0.19
    /apis
    0.17
    -ahead
    0.17
     Arnold
    0.17
    -up
    0.17
    /sm
    0.17
    slashes
    0.17
    Activations Density 0.152%

    No Known Activations