© 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. 51428
    Prev
    Next
    INDEX
    Explanations

    topics covered in courses

    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
    CCI
    -0.08
     pepp
    -0.08
     cub
    -0.08
    onto
    -0.07
    heim
    -0.07
    Ñģки
    -0.07
    essay
    -0.07
    ä¸Ģ次æĢ§
    -0.07
    ·»
    -0.07
    zz
    -0.07
    POSITIVE LOGITS
    åĬ¨æīĭ
    0.11
    å®ŀåľ°
    0.11
    贯穿
    0.10
     ÑĦоÑĢ
    0.10
    讨论
    0.09
    课åłĤæķĻåѦ
    0.09
    æľī大éĩıçļĦ
    0.09
    èĢģå¸ĪçļĦ
    0.09
    蹩
    0.09
    大éĩıçļĦ
    0.09
    Activations Density 0.072%

    No Known Activations