© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38020
    Prev
    Next
    INDEX
    Explanations

    javascript and api endpoints

    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
    大家åĪĨ享
    -0.10
    >Lorem
    -0.09
    åĵ¥
    -0.09
    å¹´ç»Ī
    -0.09
    .yy
    -0.09
    onical
    -0.08
    壮大
    -0.08
    üs
    -0.08
     маÑı
    -0.08
    .FileInputStream
    -0.08
    POSITIVE LOGITS
    ç»ĵ论
    0.10
    ãģķãģĪ
    0.08
    秩
    0.08
    cÃŃ
    0.08
    æŁ°
    0.08
    ipe
    0.08
    GetValue
    0.08
     Bram
    0.08
     subt
    0.08
    SetValue
    0.08
    Activations Density 0.164%

    No Known Activations