© 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. 30136
    Prev
    Next
    INDEX
    Explanations

    seeking something new

    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
    regon
    -0.09
    IFE
    -0.09
    razione
    -0.09
    edImage
    -0.09
    edBy
    -0.09
    è¹Ĭ
    -0.09
    acic
    -0.09
     Bentley
    -0.08
    sgiving
    -0.08
    cate
    -0.08
    POSITIVE LOGITS
    mente
    0.15
    -looking
    0.11
     جدا
    0.11
    -minded
    0.10
    çļĦ产åĵģ
    0.10
    çļĦåŃ©åŃIJ
    0.10
    çļĦä¼ģä¸ļ
    0.09
    ely
    0.09
    èĢĮåıĪ
    0.09
    çļĦåŁİå¸Ĥ
    0.09
    Activations Density 0.073%

    No Known Activations