© 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. 34367
    Prev
    Next
    INDEX
    Explanations

    billboard and signs

    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
    .dumps
    -0.11
    å£ij
    -0.09
    åłĨ积
    -0.09
    åĭĿ
    -0.09
    å¾®éĩı
    -0.09
    ÑĢаÐ
    -0.09
    æ³ĵ
    -0.09
    ÑģÑĥд
    -0.09
    atcher
    -0.09
    inz
    -0.09
    POSITIVE LOGITS
     billboard
    0.13
    广åijĬ
    0.11
     bill
    0.10
    æĭĽçīĮ
    0.09
     Billboard
    0.09
    åģĥ
    0.09
    ç«ĭéĿ¢
    0.08
    æłĩè¯Ń
    0.08
    主è¦ģåĨħ容
    0.08
    沫
    0.08
    Activations Density 0.127%

    No Known Activations