© 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. 22653
    Prev
    Next
    INDEX
    Explanations

    third parties, active in, rights remain, regional study, secure one's life, navigation devices

    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
    enville
    -0.08
    illery
    -0.08
     wzglÄĻd
    -0.08
    åĽ½å®¶å®īåħ¨
    -0.08
    丫
    -0.08
    commerce
    -0.08
    èįIJ
    -0.07
    èĹ»
    -0.07
     eskort
    -0.07
    å¼ĢåѦ
    -0.07
    POSITIVE LOGITS
     âĢŀ
    0.11
    Nr
    0.10
     und
    0.10
    âĢŀ
    0.10
     decisive
    0.09
    ç£
    0.09
    -/
    0.09
     niveau
    0.08
    _nr
    0.08
     protagonists
    0.08
    Activations Density 3.769%

    No Known Activations