© 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. 19135
    Prev
    Next
    INDEX
    Explanations

    Zope Data Pickle

    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
    常德
    -0.09
    ç½ijå°ıç¼ĸ
    -0.09
    ä¸įä¼ļåĨį
    -0.09
    iere
    -0.09
    çªł
    -0.09
    eree
    -0.08
    åĸĦ
    -0.08
    æĶ¶åī²
    -0.08
    itecture
    -0.08
    èĩ³æѤ
    -0.08
    POSITIVE LOGITS
    PEAR
    0.09
    ReadWrite
    0.09
     Elo
    0.09
    èIJ¦
    0.09
    _ABI
    0.09
     nowhere
    0.08
    _PRIV
    0.08
    lessly
    0.08
    æĻ¶
    0.08
    å´©
    0.08
    Activations Density 0.004%

    No Known Activations