© 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. 11454
    Prev
    Next
    INDEX
    Explanations

    targeting at

    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
    æĹģ
    -0.10
    orque
    -0.09
    çĺ¾
    -0.09
    лÑıÑĢ
    -0.09
    åįİå°Ķ
    -0.09
    rain
    -0.09
    ÐłÐIJ
    -0.09
    utter
    -0.09
     outgoing
    -0.08
    isman
    -0.08
    POSITIVE LOGITS
    åºŃéĻ¢
    0.10
    çķĪ
    0.09
    对çĿĢ
    0.09
    æĸ¥
    0.09
    _again
    0.09
    éĴĪ对
    0.09
    çľĻ
    0.09
    继
    0.09
    brush
    0.09
    æľīæľŁ
    0.09
    Activations Density 0.224%

    No Known Activations