© 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. 22942
    Prev
    Next
    INDEX
    Explanations

    political districts and constituencies

    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
    åĪ¹
    -0.09
    ļĮ
    -0.08
    hoa
    -0.08
    ®
    -0.08
     kla
    -0.08
    寻
    -0.08
    compound
    -0.08
     compound
    -0.07
    èħ¾
    -0.07
    нÑı
    -0.07
    POSITIVE LOGITS
    åĩºåĽ½çķĻåѦ
    0.11
    entr
    0.09
    娴
    0.09
    æĮ«
    0.09
    å²Ĺä½į
    0.09
    anni
    0.09
    usted
    0.09
    imb
    0.09
    ä¹Ķ
    0.09
     GOT
    0.09
    Activations Density 0.077%

    No Known Activations