© 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. 27831
    Prev
    Next
    INDEX
    Explanations

    making a choice or decision

    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
    åīĬ
    -0.10
    å¹²
    -0.09
    èįĴ
    -0.09
    ç¥ļ
    -0.08
    误导
    -0.08
    .plist
    -0.08
    诱æĥij
    -0.08
    legg
    -0.08
    BOOLE
    -0.08
     cams
    -0.08
    POSITIVE LOGITS
    ATA
    0.09
    åĨ³å®ļ
    0.09
    好åĩłä¸ª
    0.09
    0
    0.09
    æĢ§åij½
    0.09
    åĨ³ä¸į
    0.09
    åĿ³
    0.09
    åİ»è¿ĩ
    0.08
    çĶŁæ´»çļĦ
    0.08
    æݥ纳
    0.08
    Activations Density 0.027%

    No Known Activations