© 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. 1827
    Prev
    Next
    INDEX
    Explanations

    fine furniture, wine, dining, photos, examples, British, Print, china, coins

    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
    itel
    -0.08
     CI
    -0.08
    好好
    -0.08
    adier
    -0.08
    CI
    -0.08
    忧èĻij
    -0.08
    åŁİéĻħ
    -0.08
    èIJ¥éĢłèī¯å¥½
    -0.08
    lex
    -0.08
    oma
    -0.08
    POSITIVE LOGITS
    anga
    0.10
    erce
    0.10
    鸾
    0.10
    åºł
    0.09
    erged
    0.09
    çĪµ
    0.09
    èİ«è¿ĩäºİ
    0.09
    éĦľ
    0.09
    SetActive
    0.09
    dess
    0.09
    Activations Density 0.007%

    No Known Activations