© 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. 36108
    Prev
    Next
    INDEX
    Explanations

    axillary, axial, axles

    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
    袤
    -0.10
    ç¼ĥ
    -0.10
    æĥº
    -0.09
    egin
    -0.09
    رÙĬ
    -0.09
    å¸ĤåĢ¼
    -0.08
    ä¸įèµ·
    -0.08
    eenth
    -0.08
    MLS
    -0.08
    裤
    -0.08
    POSITIVE LOGITS
    /or
    0.12
    0.11
    illary
    0.10
    ymmetric
    0.08
    èĤĺ
    0.08
    awesome
    0.08
    å®°
    0.08
     serialVersionUID
    0.08
    ä»·
    0.08
    ilent
    0.08
    Activations Density 0.033%

    No Known Activations