© 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. 23545
    Prev
    Next
    INDEX
    Explanations

    data and dataset availability

    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
    amax
    -0.10
    åĥ§
    -0.09
     autof
    -0.09
    è¦ģéĹ»
    -0.09
    åĵį
    -0.08
     diamond
    -0.08
    isas
    -0.08
    .tagName
    -0.08
     getParent
    -0.08
    ForObject
    -0.08
    POSITIVE LOGITS
     dataset
    0.14
    æķ°æį®
    0.14
     datasets
    0.13
     data
    0.13
    ãĥĩãĥ¼ãĤ¿
    0.13
    data
    0.12
    .dataset
    0.11
    å¼ĢåıijåĪ©çĶ¨
    0.11
    æķ¸æĵļ
    0.11
    ë
    0.11
    Activations Density 0.174%

    No Known Activations