© 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. 53973
    Prev
    Next
    INDEX
    Explanations

    function properly

    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
    orca
    -0.10
    izon
    -0.09
    ander
    -0.09
    çĶ¨æĪ·æıIJä¾Ľ
    -0.09
    LAG
    -0.09
    imit
    -0.08
     lá»Ńa
    -0.08
    èĿ®
    -0.08
    ä»»æķĻ
    -0.08
    à¹īà¸Ńà¸ĩ
    -0.08
    POSITIVE LOGITS
    ally
    0.12
    èĩªå¦Ĥ
    0.11
    uar
    0.10
    å¾Ĥ
    0.09
    ä¸įä½³
    0.09
    Į¨
    0.09
    elsing
    0.09
    nement
    0.09
    uate
    0.09
    åħ®
    0.09
    Activations Density 0.051%

    No Known Activations