© 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. 53749
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
    atti
    -0.12
    Ó¨
    -0.10
    omy
    -0.10
    çĵľ
    -0.09
     quo
    -0.09
    å»Ł
    -0.09
    峤
    -0.09
    ány
    -0.08
    /OR
    -0.08
    .createObject
    -0.08
    POSITIVE LOGITS
    ä¹ĭå¤ĸ
    0.12
     alongside
    0.11
     besides
    0.11
     oltre
    0.11
    éĻ¤äºĨ
    0.10
    ä¸įä»ħè¦ģ
    0.09
    à¸Ļà¸Ńà¸ģà¸Īาà¸ģ
    0.09
    Along
    0.09
     Along
    0.09
     along
    0.09
    Activations Density 0.089%

    No Known Activations