© 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. 49966
    Prev
    Next
    INDEX
    Explanations

    pretty much or quite a

    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
    ÙĪاÙĨ
    -0.09
    éĢŀ
    -0.09
    GRP
    -0.09
    å·²ä¹ħçļĦ
    -0.09
    èµħ
    -0.09
    ipy
    -0.09
    çĴľ
    -0.09
    骥
    -0.09
    æīĢ说çļĦ
    -0.09
    èĥ½ä¸įèĥ½
    -0.08
    POSITIVE LOGITS
    æĶ¶åĪ°äºĨ
    0.10
    åīįåIJİ
    0.09
    èĩ³ä¸Ĭ
    0.09
    æĻ´
    0.09
    èĽ®
    0.08
    åĸij
    0.08
    (Unit
    0.08
    asting
    0.08
    .options
    0.08
    -io
    0.08
    Activations Density 0.024%

    No Known Activations