© 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. 33083
    Prev
    Next
    INDEX
    Explanations

    Gilbert and Sullivan

    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
    ials
    -0.13
    åĭĥåĭĥ
    -0.11
    å¥ij
    -0.09
    pei
    -0.09
    odor
    -0.09
    OnError
    -0.08
    ÙĬÙĥا
    -0.08
    åŀĴ
    -0.08
    cade
    -0.08
    æµ·æ¹¾
    -0.08
    POSITIVE LOGITS
    0.10
    çķ´
    0.10
    ycl
    0.09
    ãģªãģı
    0.09
    eness
    0.09
    èĹ»
    0.09
     ÃŃch
    0.09
    many
    0.09
    son
    0.09
    maid
    0.09
    Activations Density 0.007%

    No Known Activations