© 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. 10112
    Prev
    Next
    INDEX
    Explanations

    watering hole, enticing

    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
    ACHI
    -0.10
    à¥į
    -0.10
    ually
    -0.09
    碴
    -0.09
     Trafford
    -0.09
    itti
    -0.09
    unu
    -0.09
    AREN
    -0.08
    ÑıÑĤÑģÑı
    -0.08
    itto
    -0.08
    POSITIVE LOGITS
    æľĽåİ»
    0.10
    诱人
    0.09
    اس
    0.09
    sgi
    0.09
    åĭĥåĭĥ
    0.09
    樯
    0.08
    åĿĬ
    0.08
    iki
    0.08
    åĪ
    0.08
    bread
    0.08
    Activations Density 0.002%

    No Known Activations