© 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. 34120
    Prev
    Next
    INDEX
    Explanations

    names of authors or people

    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
    elon
    -0.10
    WindowState
    -0.09
    iap
    -0.09
    verted
    -0.09
    elijk
    -0.09
     MessageBoxIcon
    -0.09
    quent
    -0.09
    elog
    -0.08
    HAM
    -0.08
    åĥµ
    -0.08
    POSITIVE LOGITS
    ssel
    0.09
    isters
    0.09
    à¹Ģà¸Ńà¸ĩ
    0.08
    æ°¸ä¹ħ
    0.08
    .Imp
    0.08
    çģ¶
    0.08
    çݯçIJĥ
    0.08
    åģľçķĻåľ¨
    0.08
    èĢĨ
    0.08
     Candle
    0.08
    Activations Density 0.004%

    No Known Activations