© 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. 1541
    Prev
    Next
    INDEX
    Explanations

    airways, ductal, obstruct

    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
    éĻIJ度
    -0.10
    eson
    -0.10
    cir
    -0.10
    opsis
    -0.09
    éŨå¤ĸ
    -0.09
    วà¸ĩ
    -0.09
    ä»ĸèĩªå·±
    -0.09
    éĹª
    -0.09
    ç§Ģ
    -0.09
    sworth
    -0.09
    POSITIVE LOGITS
    æ±Ĺ
    0.10
     SEEK
    0.09
    ething
    0.09
    çħ§
    0.08
    æݥ触
    0.08
    inary
    0.08
    itemap
    0.08
    åł¡
    0.08
    олод
    0.08
    ilo
    0.08
    Activations Density 0.506%

    No Known Activations