© 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. 5298
    Prev
    Next
    INDEX
    Explanations

    "puppet" "onto" "Rage"

    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
    åIJ¬åĬĽ
    -0.10
    edor
    -0.10
    读æĩĤ
    -0.10
     SOUR
    -0.09
    olen
    -0.09
    æĬĬæĮģ
    -0.08
    çİ©
    -0.08
     Invent
    -0.08
     Play
    -0.08
    æĶ¶åıĸ
    -0.08
    POSITIVE LOGITS
    çī¹æķĪ
    0.12
    æĭįæijĦ
    0.10
    亲
    0.10
    骡
    0.10
    vla
    0.10
    éŀį
    0.10
    ä»Ļå¢ĥ
    0.10
     наÑĤÑĥÑĢ
    0.10
    åī§ç»Ħ
    0.09
    doch
    0.09
    Activations Density 0.117%

    No Known Activations