© 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. 63356
    Prev
    Next
    INDEX
    Explanations

    Requests for materials

    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
    assen
    -0.09
    à¹īม
    -0.08
    ROP
    -0.08
    ersed
    -0.08
     tackles
    -0.07
    frag
    -0.07
    奥巴
    -0.07
    NE
    -0.07
    è¿Ļä¹Īå¤ļ
    -0.07
     اÙĦØ°
    -0.07
    POSITIVE LOGITS
    ä¸Ģå¾ĭ
    0.11
    æĽĻ
    0.10
    çĭ¬å®¶
    0.09
    eria
    0.09
    æ´Ĺ礼
    0.09
    via
    0.09
    å·²ä¹ħçļĦ
    0.09
    .bio
    0.09
    åľºéĿ¢
    0.09
    quez
    0.09
    Activations Density 0.026%

    No Known Activations