© 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. 50012
    Prev
    Next
    INDEX
    Explanations

    digital advertising or marketing

    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
    orate
    -0.09
    个åĪ«
    -0.09
    reat
    -0.09
    潦
    -0.09
    _impl
    -0.09
    æįŁ
    -0.09
    inz
    -0.09
    ancel
    -0.09
    æIJį
    -0.09
     dam
    -0.09
    POSITIVE LOGITS
    9
    0.09
    uve
    0.09
    5
    0.09
    1
    0.09
    è¾Ĺ
    0.09
    7
    0.09
    2
    0.09
    8
    0.09
    é³
    0.08
    交ä¼ļ
    0.08
    Activations Density 0.074%

    No Known Activations