© 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. 32071
    Prev
    Next
    INDEX
    Explanations

    submission documents

    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
    ä¾ij
    -0.10
    ç£ģåľº
    -0.10
    _TA
    -0.09
    æıIJæĭĶ
    -0.09
    ritis
    -0.09
    asive
    -0.09
    ç¼
    -0.09
    èį©
    -0.09
     ÐijÑĢ
    -0.09
    Õ¼
    -0.08
    POSITIVE LOGITS
    è¯ģæĺİ
    0.14
    é½IJåħ¨
    0.13
    åİŁä»¶
    0.13
    å½±
    0.12
    èŃīæĺİ
    0.12
    å¤įåį°ä»¶
    0.11
     documents
    0.11
    è¯ģ件
    0.11
     proof
    0.11
    æĿIJæĸĻ
    0.11
    Activations Density 0.078%

    No Known Activations