© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21028
    Prev
    Next
    INDEX
    Explanations

    numbers and roman numerals

    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
    è¿ŀ线
    -0.10
    å¿Ļ
    -0.10
    bole
    -0.10
    ovo
    -0.09
     Juliet
    -0.08
    èĥ±
    -0.08
    ä¸ĢéŨ
    -0.08
    ãģ°
    -0.08
     listings
    -0.08
    grund
    -0.08
    POSITIVE LOGITS
    åı·
    0.11
    éĤ£æ¬¡
    0.11
    ityEngine
    0.09
    次æķ°
    0.09
    PLICATION
    0.09
    -runner
    0.08
    ä¸Ģ次
    0.08
    FACE
    0.08
    .generated
    0.08
     mop
    0.08
    Activations Density 0.099%

    No Known Activations