© 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. 54943
    Prev
    Next
    INDEX
    Explanations

    phone number

    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
    åħ¬è®¤
    -0.09
    å·²ä¹ħçļĦ
    -0.09
    å®°
    -0.09
    oval
    -0.09
    为代表
    -0.09
    åĨ¬å¥¥
    -0.08
    æıĸ
    -0.08
    æŶéĹ´åĨħ
    -0.08
     Extr
    -0.08
    çļĦå¿ĥæĥħ
    -0.08
    POSITIVE LOGITS
    çĨ
    0.10
     ÑĤелеÑĦ
    0.09
    æľīæķĪæľŁ
    0.08
     SIG
    0.08
    igit
    0.08
     Osw
    0.08
    ä¸ĢæľŁ
    0.08
    ä¼łå¥ĩ
    0.08
     Oc
    0.08
    å¦Ĥä½ķ
    0.08
    Activations Density 0.007%

    No Known Activations