© 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. 52179
    Prev
    Next
    INDEX
    Explanations

    takes time and effort

    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
    ·»
    -0.11
     pil
    -0.10
    声称
    -0.10
     McCabe
    -0.10
    pine
    -0.09
    onna
    -0.09
    èĬĿåĬłåĵ¥
    -0.09
    аниÑİ
    -0.09
    çļĦ人çĶŁ
    -0.09
    lund
    -0.09
    POSITIVE LOGITS
    大家
    0.09
    åij³
    0.09
    æ°
    0.08
    å¤ļå°ij
    0.08
    s
    0.08
    æĪij
    0.08
    æĪijåİ»
    0.08
    æĪij们
    0.08
     him
    0.08
    .TryParse
    0.08
    Activations Density 0.013%

    No Known Activations