© 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. 9976
    Prev
    Next
    INDEX
    Explanations

    spinal cord and surgery

    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
    çĪ
    -0.09
    Ùĥر
    -0.09
    ../../../
    -0.08
     cyn
    -0.08
    edom
    -0.08
    orie
    -0.08
    æĹ¶æľº
    -0.08
    empt
    -0.08
    们
    -0.08
    ói
    -0.08
    POSITIVE LOGITS
    arity
    0.10
    幡
    0.10
     spine
    0.10
    yard
    0.10
    ridden
    0.09
    èĦĬ
    0.09
    å®īåħ¨ä¿Ŀéļľ
    0.09
    åĮĹ京åĨ¬å¥¥
    0.09
    Bindable
    0.09
    ãģĹãģ¾
    0.09
    Activations Density 0.030%

    No Known Activations