© 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. 57413
    Prev
    Next
    INDEX
    Explanations

    wood, furniture, and finishes

    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
    寮
    -0.11
    èķĥ
    -0.10
    说èĩªå·±
    -0.10
    /copyleft
    -0.10
     khám
    -0.10
    害ç¾ŀ
    -0.10
    失æķĪ
    -0.10
    éķŀ
    -0.10
    ä¸Ģ大åłĨ
    -0.09
    åĺ¹
    -0.09
    POSITIVE LOGITS
     furniture
    0.12
    家åħ·
    0.12
     Furniture
    0.10
     antique
    0.09
    仿
    0.09
    åĦ¿
    0.08
     Rays
    0.08
    urniture
    0.08
    çłį
    0.07
    ried
    0.07
    Activations Density 0.158%

    No Known Activations