© 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. 17560
    Prev
    Next
    INDEX
    Explanations

    introductions and qualifications

    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
    ä¸Ģä¸ĸ
    -0.08
    漫
    -0.08
    æ³Į
    -0.08
    åĵĩ
    -0.08
    _geom
    -0.08
    鬲
    -0.08
    éĻ
    -0.08
    æĪijåİ»
    -0.07
    带走
    -0.07
    æ·ĺ
    -0.07
    POSITIVE LOGITS
    åłĩ
    0.11
    åı£å¾Ħ
    0.10
    å¿ĻçĿĢ
    0.09
    WND
    0.09
    .addAction
    0.09
    æ¸ħçĪ½
    0.08
    æķ¬è¯·
    0.08
    æľīç½ijåıĭ
    0.08
    çī¹æ´¾
    0.08
    _logic
    0.08
    Activations Density 0.233%

    No Known Activations