© 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. 19233
    Prev
    Next
    INDEX
    Explanations

    posts and threads

    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
    /MIT
    -0.10
    svc
    -0.09
    鸾
    -0.09
    å¾Ĺå¾Ī
    -0.09
     din
    -0.08
    _ov
    -0.08
    讫
    -0.08
    ä»ĭ
    -0.08
     camping
    -0.08
    æĦı大
    -0.08
    POSITIVE LOGITS
    _BACKEND
    0.09
    uhan
    0.09
    è°İ
    0.09
    ä¸Ĭæľī
    0.09
    _THREADS
    0.09
    toList
    0.09
    çĶļèĩ³æĺ¯
    0.09
    éĻĦè¿ijçļĦ
    0.08
    è¿Ŀ
    0.08
    çī¹åĪ«å£°æĺİ
    0.08
    Activations Density 0.005%

    No Known Activations