© 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. 11954
    Prev
    Next
    INDEX
    Explanations

    perspective, benefits, preferences, discounted, Our, Fourth, direct

    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
    Reservation
    -0.10
    åĸ§
    -0.10
    èĩªåĬ©
    -0.09
     panc
    -0.09
    å¡ijæĸĻ
    -0.09
    DEX
    -0.09
     Shack
    -0.09
    åĸ½
    -0.09
    å¿Ĩ
    -0.08
    åŁºå±Ĥ
    -0.08
    POSITIVE LOGITS
    串
    0.10
    éĻª
    0.09
    UTOR
    0.09
    رÙĬÙĨ
    0.09
    asury
    0.08
    ä¿¡
    0.08
     haz
    0.08
    ç²¾ç¥ŀ
    0.08
    taire
    0.08
     toll
    0.08
    Activations Density 0.095%

    No Known Activations