© 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. 50335
    Prev
    Next
    INDEX
    Explanations

    treatment of or as

    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
    èĢĥèĻijåĪ°
    -0.09
    OrUpdate
    -0.09
    ä½ĵèĤ²åľº
    -0.09
    ç½ijåıĭ们
    -0.09
    æ¨Ĭ
    -0.09
    itude
    -0.09
    讹
    -0.08
    ÑģÑĤÑĢа
    -0.08
    èµĮ
    -0.08
    åĩºæīĭ
    -0.08
    POSITIVE LOGITS
    对å¾ħ
    0.11
    aker
    0.08
     ž
    0.08
    ä»Ļ女
    0.08
    _ie
    0.08
    å¤ĩ
    0.08
    ORY
    0.08
    è´¢åĬ¡ç®¡çIJĨ
    0.08
    kur
    0.08
    åĪĨæѧ
    0.08
    Activations Density 0.035%

    No Known Activations