© 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. 61966
    Prev
    Next
    INDEX
    Explanations

    groups of people or items

    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
    æ´½
    -0.11
    enic
    -0.10
     Dich
    -0.10
    .bs
    -0.09
    两家
    -0.09
    ä¸ī家
    -0.09
    jiang
    -0.09
    .mj
    -0.09
    moil
    -0.09
    åıĮéĩį
    -0.09
    POSITIVE LOGITS
    ç»Ħéķ¿
    0.17
    å°ıç»Ħ
    0.14
    ç»Ħ
    0.13
    ä¸Ģç»Ħ
    0.11
    çµĦ
    0.10
     groups
    0.10
    æī¿æĭħ
    0.09
    -groups
    0.09
    tract
    0.09
    groups
    0.09
    Activations Density 0.068%

    No Known Activations