© 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. 32443
    Prev
    Next
    INDEX
    Explanations

    high throughput

    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
    åıijçĥ§
    -0.12
    loth
    -0.11
    åĭĥåĭĥ
    -0.11
    ŀ
    -0.10
    acher
    -0.10
    adies
    -0.09
    GLE
    -0.09
    æĹĥ
    -0.09
    èĥ¥
    -0.09
    ihu
    -0.09
    POSITIVE LOGITS
    æł¸å®ļ
    0.09
    olis
    0.09
    ri
    0.08
    ç²¾åĬĽ
    0.08
    å¾ĹäºĨ
    0.08
     Cook
    0.08
    å¿ĥ仪
    0.08
    æ¼Ĩ
    0.07
     Lov
    0.07
    å¯Ĵ
    0.07
    Activations Density 0.002%

    No Known Activations