© 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. 54846
    Prev
    Next
    INDEX
    Explanations

    so many

    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
    äºĨä¸įå°ij
    -0.10
    æĺ¯æĪij
    -0.08
    ä¸įå°ıçļĦ
    -0.08
    å·ŀåĮº
    -0.08
     fm
    -0.08
    ãģĦãģ¾
    -0.08
    asted
    -0.08
    emd
    -0.08
    stable
    -0.08
    æīĢæľīæĿĥ
    -0.08
    POSITIVE LOGITS
    uded
    0.11
    ething
    0.10
    -called
    0.10
    oth
    0.09
    ftware
    0.09
    hots
    0.09
    aying
    0.09
    /all
    0.09
    quence
    0.08
     же
    0.08
    Activations Density 0.010%

    No Known Activations