© 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. 30858
    Prev
    Next
    INDEX
    Explanations

    obtained from or isolated

    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
    éĹ©
    -0.09
    å²Ĺ
    -0.09
    بÙĪر
    -0.08
     Bands
    -0.08
    led
    -0.08
    oot
    -0.08
    ields
    -0.08
    esimal
    -0.08
    æļĤ
    -0.08
    æľīä¸ĢäºĽ
    -0.08
    POSITIVE LOGITS
    æĬ½åıĸ
    0.12
    éĤ£åĦ¿
    0.10
    æĮĸæİĺ
    0.10
    æijĺ
    0.10
    è¦ģåĬłå¼º
    0.09
    åĵªåĦ¿
    0.09
    俸
    0.09
    æĢ»æĶ¶åħ¥
    0.09
    åĩºèĩª
    0.09
    ÑĨÑĥ
    0.09
    Activations Density 0.352%

    No Known Activations