© 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. 58639
    Prev
    Next
    INDEX
    Explanations

    passengers in vehicles

    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
    奸
    -0.10
    èĩªå¾ĭ
    -0.10
    رÙĥ
    -0.10
    ijk
    -0.09
    ark
    -0.09
    heimer
    -0.09
    æĶ¹è¿Ľ
    -0.09
    ä¸īä½įä¸Ģä½ĵ
    -0.09
    åı¤ä»Ĭ
    -0.08
    âĢ¾
    -0.08
    POSITIVE LOGITS
    -side
    0.09
    ENTE
    0.08
    -language
    0.08
     ëħ
    0.08
    .Align
    0.08
    .lex
    0.08
    ä¸į失
    0.08
     Manson
    0.08
    Shield
    0.08
    hip
    0.07
    Activations Density 0.008%

    No Known Activations