© 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. 23557
    Prev
    Next
    INDEX
    Explanations

    he followed by 'age' or 'Houston'

    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
     tier
    -0.09
    梯éĺŁ
    -0.08
    ä¸Ģé¢Ĺ
    -0.08
    tern
    -0.08
    (CC
    -0.08
    èµĦ
    -0.08
    èĽĽ
    -0.08
    ä½ĵè´´
    -0.08
    tier
    -0.08
    è¯ļæĦı
    -0.08
    POSITIVE LOGITS
    uffers
    0.09
    bbing
    0.08
     leng
    0.08
    âĨķ
    0.08
    USIC
    0.08
    对å¾ħ
    0.08
    onomic
    0.08
    å¹´é¾Ħ段
    0.08
    urent
    0.08
    çµĦ
    0.08
    Activations Density 0.023%

    No Known Activations