© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50477
    Prev
    Next
    INDEX
    Explanations

    Melbournepoints of interest

    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
    æ»
    -0.10
    adal
    -0.09
    arkin
    -0.09
    stant
    -0.09
    ı
    -0.09
    adge
    -0.09
    ymb
    -0.09
    opr
    -0.08
    нÑĤеÑĢ
    -0.08
    ãĥĹ
    -0.08
    POSITIVE LOGITS
    éĻ¤æѤ
    0.12
    åķī
    0.11
    åİ®
    0.10
    æ±¹
    0.10
    íĮ©
    0.09
    ä¸ĢæĬ¹
    0.09
    欧å¼ı
    0.09
    èŀ«
    0.09
    ÙĬÙĦÙĬ
    0.09
    ä¸Ģçľĭ
    0.09
    Activations Density 0.006%

    No Known Activations