© 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. 32493
    Prev
    Next
    INDEX
    Explanations

    affirmative responses and agreements

    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
    åĭĭ
    -0.09
    éĩįçĤ¹
    -0.08
     Fed
    -0.08
    -Sep
    -0.08
    IBC
    -0.08
    åĨį度
    -0.08
    (pattern
    -0.08
    æĺ¯çĶ¨æĿ¥
    -0.07
    ERN
    -0.07
    -Sah
    -0.07
    POSITIVE LOGITS
    åĿIJä¸ĭ
    0.10
     agreed
    0.10
    æĦ¿æľĽ
    0.10
     agreeing
    0.10
     agree
    0.10
    è¯ķè¯ķ
    0.10
    åIJĮæĦı
    0.10
    æĭįæĭį
    0.10
    æĦ¿æĦı
    0.10
    íķĺê²łëĭ¤
    0.09
    Activations Density 0.036%

    No Known Activations