© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35438
    Prev
    Next
    INDEX
    Explanations

    increase or intensify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æľĶ
    -0.10
    BMI
    -0.09
    ä¹Łä¸º
    -0.09
    igers
    -0.09
    ä¹Łå¥½
    -0.09
     Cald
    -0.09
    ä»İæł¹æľ¬
    -0.09
    avez
    -0.08
    lat
    -0.08
    ALAR
    -0.08
    POSITIVE LOGITS
    åĬĽåº¦
    0.14
    åĬłå¤§
    0.10
    åĬłç´§
    0.10
    æĶ¯æĮģåĬĽåº¦
    0.10
    ikki
    0.09
    è¦ģåĬłå¼º
    0.09
    åĬłå¿«
    0.09
    åĬłå¤§å¯¹
    0.09
    æĬķåħ¥
    0.09
    ä¹ĭåĬ¿
    0.09
    Activations Density 0.058%

    No Known Activations