© 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. 10696
    Prev
    Next
    INDEX
    Explanations

    academic fields and technology

    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
    oud
    -0.19
     pinch
    -0.19
    æīĭæĮģ
    -0.19
    azzo
    -0.19
    lien
    -0.19
    ä¸Ģå¿ĥ
    -0.18
    mars
    -0.18
    ç°ł
    -0.18
    idal
    -0.18
    ida
    -0.18
    POSITIVE LOGITS
    Instrument
    0.20
    åħ¶å®ĥéĹ®é¢ĺ
    0.20
    访è°Ī
    0.19
    ç»ı纬
    0.18
    èģĶ
    0.18
    仪
    0.18
    缸åħ³æĶ¿çŃĸ
    0.18
    ç±»
    0.18
    Abb
    0.18
    Behavior
    0.17
    Activations Density 0.249%

    No Known Activations