© 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. 52612
    Prev
    Next
    INDEX
    Explanations

    Brit, Britt, Brittany

    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
    OrUpdate
    -0.12
    itive
    -0.10
    erah
    -0.09
    åŁĶ
    -0.09
    羣çIJĨ
    -0.09
     james
    -0.09
    æIJ¦
    -0.09
    ç°¸
    -0.09
    å¾Ĺ天
    -0.09
    åĽŀåIJĪ
    -0.09
    POSITIVE LOGITS
    gems
    0.12
    ely
    0.10
    aceous
    0.10
    IQUE
    0.09
    isque
    0.09
    že
    0.09
    -minded
    0.09
    对å¾ħ
    0.09
    Į
    0.09
    aly
    0.08
    Activations Density 0.006%

    No Known Activations