© 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. 52433
    Prev
    Next
    INDEX
    Explanations

    formal classroom learning settings

    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
    çĶ¨å¾®ä¿¡
    -0.10
    微信åı·
    -0.09
    oscope
    -0.09
    ä¾ĽéľĢ
    -0.09
    _scope
    -0.09
     Rider
    -0.08
    _De
    -0.08
    .Must
    -0.08
    éķľåŃIJ
    -0.08
    lap
    -0.08
    POSITIVE LOGITS
    课åłĤ
    0.13
    ä¸ĬåѦ
    0.12
    æŃ£è§Ħ
    0.11
    课åłĤæķĻåѦ
    0.11
     classroom
    0.10
     formal
    0.10
    çŁ¥è¯Ĩ
    0.09
     cir
    0.09
     Settings
    0.09
     settings
    0.09
    Activations Density 0.059%

    No Known Activations