© 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. 5620
    Prev
    Next
    INDEX
    Explanations

    hallucinations, delusions, LSD, illusions

    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
     dõi
    -0.10
    batim
    -0.09
    ness
    -0.09
    orr
    -0.09
    人家
    -0.09
     pháºŃn
    -0.09
    иÑĢовка
    -0.09
    ãĥ¼
    -0.09
    OTH
    -0.08
    ASY
    -0.08
    POSITIVE LOGITS
    elix
    0.08
    ç¾ļ
    0.08
     maté
    0.08
    彩
    0.08
    æ¨Ł
    0.08
    åĬ¬
    0.08
    elic
    0.08
    isan
    0.08
    æľīç½ijåıĭ
    0.08
     gums
    0.08
    Activations Density 0.003%

    No Known Activations