© 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. 13408
    Prev
    Next
    INDEX
    Explanations

    people, places, or things

    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
    etal
    -0.21
    以åıĬåħ¶ä»ĸ
    -0.21
     Sher
    -0.20
    Interop
    -0.20
    è§Ī
    -0.20
    afe
    -0.20
    ä¸įç»ı
    -0.19
    Äħd
    -0.19
    åıĬåħ¶ä»ĸ
    -0.18
    mage
    -0.18
    POSITIVE LOGITS
     BASIS
    0.19
    çĽĴ
    0.19
    ĥģ
    0.19
     Duty
    0.19
    æªĢ
    0.18
    å±¥è¡Į
    0.18
    æħĬ
    0.18
    æ¤ģ
    0.17
    [ch
    0.17
    è¿ĺ好
    0.17
    Activations Density 0.259%

    No Known Activations