© 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. 6318
    Prev
    Next
    INDEX
    Explanations

    set up the environment

    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
    åģĥ
    -0.09
    äºķ
    -0.08
    æļ¨
    -0.08
    è°ĥèĬĤ
    -0.08
    忽çĦ¶
    -0.08
    anker
    -0.08
    achat
    -0.08
     dispens
    -0.08
    åĪĹ表
    -0.08
    айн
    -0.08
    POSITIVE LOGITS
    rig
    0.10
    éĻ©
    0.09
    å¥łå®ļäºĨ
    0.09
    继
    0.09
    ä¸įåĪ©
    0.09
    æĪIJåĬŁçİĩ
    0.09
     Failure
    0.09
    æ®Ĩ
    0.09
     failure
    0.09
    é¢Ĩè¡Ķ
    0.09
    Activations Density 0.171%

    No Known Activations