© 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. 17381
    Prev
    Next
    INDEX
    Explanations

    Berkshire, Perkins, Bergeron

    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
    æĪijåİ»
    -0.11
    oons
    -0.11
     Nolan
    -0.09
    lings
    -0.09
    书记
    -0.09
    ivia
    -0.09
    æĪijå°±
    -0.08
    éºĩ
    -0.08
    leness
    -0.08
    çĶľ
    -0.08
    POSITIVE LOGITS
    yc
    0.11
    寿åij½
    0.09
    人寿
    0.08
    sim
    0.08
    ../
    0.08
     Hath
    0.08
    iles
    0.08
    Ñıв
    0.08
    sr
    0.08
    ury
    0.08
    Activations Density 0.003%

    No Known Activations