© 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. 4421
    Prev
    Next
    INDEX
    Explanations

    italian origin

    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
    æŀ¯çĩ¥
    -0.10
    æĿŀ
    -0.10
    åŃij
    -0.09
    /Instruction
    -0.09
    æ´¥
    -0.09
    ä¹Ŀæ±Ł
    -0.09
    åİ¥
    -0.09
    屯
    -0.09
    TTY
    -0.09
    çĩ§
    -0.09
    POSITIVE LOGITS
    æĦı大åĪ©
    0.23
     Italian
    0.20
    Italian
    0.18
     Italy
    0.16
    Italy
    0.16
     Italians
    0.15
     italian
    0.14
    èĭıå·ŀå¸Ĥ
    0.13
    å¨ģå°¼æĸ¯
    0.13
    ç±³åħ°
    0.13
    Activations Density 0.415%

    No Known Activations