© 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. 61250
    Prev
    Next
    INDEX
    Explanations

    two thirds

    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
    象
    -0.09
    ãĢħ
    -0.08
    äºĨå¤ļå°ij
    -0.08
    æĺ¯ä¸Ģ座
    -0.08
    æĬ«
    -0.08
    ãģĭãĤĮ
    -0.08
    ëł¹
    -0.08
    Fab
    -0.08
    ei
    -0.08
    oly
    -0.07
    POSITIVE LOGITS
    滥
    0.10
    dra
    0.09
    enson
    0.09
     cục
    0.09
     Stones
    0.09
    лин
    0.09
    Nu
    0.08
    çѱ
    0.08
    æ¾į
    0.08
    eras
    0.08
    Activations Density 0.005%

    No Known Activations