© 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. 4382
    Prev
    Next
    INDEX
    Explanations

    is a

    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
    sn
    -0.09
    isque
    -0.09
    1
    -0.09
    8
    -0.09
    两个人
    -0.09
    åIJĸ
    -0.09
    éļª
    -0.09
    2
    -0.09
    0
    -0.09
    é¦Ķ
    -0.09
    POSITIVE LOGITS
    clud
    0.09
     vent
    0.08
    ä»ĸä¹Ł
    0.08
    emain
    0.08
    itness
    0.08
     нем
    0.08
    oplay
    0.08
    -framework
    0.07
    å°ĨåĨĽ
    0.07
    ÑģÑı
    0.07
    Activations Density 0.068%

    No Known Activations