© 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. 30087
    Prev
    Next
    INDEX
    Explanations

    colleges of departments

    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
     Inquiry
    -0.08
    TEAM
    -0.08
    team
    -0.08
    åŃĿ
    -0.08
    论
    -0.08
    课é¢ĺ
    -0.08
    àªĩ
    -0.08
     Osw
    -0.08
    auge
    -0.08
    uml
    -0.07
    POSITIVE LOGITS
    éĥ¨éŨ
    0.13
    éĥ¨éĸĢ
    0.11
    ussen
    0.10
    åıĪ好
    0.10
    Dean
    0.09
    èģĮèĥ½éĥ¨éŨ
    0.09
    éĻ¢éķ¿
    0.09
    Depart
    0.09
    æĶ¶åĪ°äºĨ
    0.09
    èį¤
    0.09
    Activations Density 0.105%

    No Known Activations