© 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. 31366
    Prev
    Next
    INDEX
    Explanations

    Clyde, ford, Pulford, Clydesdale

    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
    ве
    -0.10
    ãģij
    -0.09
    بÙĨ
    -0.09
    ä¸Ģç¬Ķ
    -0.09
    æľīæ¯Ĵ
    -0.09
    å®ļäºĨ
    -0.09
    ãĥ³ãĤ°
    -0.08
    gable
    -0.08
    大æĸ¹
    -0.08
    æĪ¿ä¸ľ
    -0.08
    POSITIVE LOGITS
    iture
    0.09
    åĿı
    0.09
    .respond
    0.08
    对æĬĹ
    0.08
    éĤ£ä½ł
    0.08
    æ·Ģç²ī
    0.08
    markt
    0.08
    ária
    0.08
    adt
    0.08
     either
    0.08
    Activations Density 0.004%

    No Known Activations