© 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. 39562
    Prev
    Next
    INDEX
    Explanations

    bachelor's degree

    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
    CTION
    -0.10
    ilent
    -0.08
    enment
    -0.08
    aceous
    -0.08
     cầu
    -0.08
    ocrates
    -0.08
    igel
    -0.08
    iability
    -0.08
    pecially
    -0.08
    parable
    -0.08
    POSITIVE LOGITS
    hood
    0.11
    èĢ½
    0.10
    ship
    0.10
     Revenge
    0.10
    模èĮĥ
    0.09
    itas
    0.09
    loo
    0.09
    긴
    0.09
    ä¸Ģçŀ¬éĹ´
    0.09
    ä»Ģä¹Īåı«
    0.09
    Activations Density 0.010%

    No Known Activations