© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37712
    Prev
    Next
    INDEX
    Explanations

    energy production and materials

    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
    奢
    -0.08
    åŀĤ
    -0.08
     POD
    -0.08
    sg
    -0.08
    bir
    -0.08
    穹
    -0.08
    çĶµåĻ¨
    -0.08
    ç§ĭ天
    -0.08
    conomy
    -0.08
    å±ł
    -0.08
    POSITIVE LOGITS
    insk
    0.10
    rances
    0.09
    ä¸į大
    0.09
    ä¿ĿèįIJ
    0.09
    tesy
    0.09
    à¸ķะ
    0.09
    éħ½
    0.09
    åĽŀæĥ³
    0.09
    vern
    0.09
    roe
    0.08
    Activations Density 0.099%

    No Known Activations