© 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. 27084
    Prev
    Next
    INDEX
    Explanations

    create or make something

    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
    çĭIJ
    -0.09
    èķĥ
    -0.08
    饱
    -0.08
    ä¸Ģçľĭ
    -0.08
    3
    -0.08
    é¦ĸ
    -0.08
     pyramid
    -0.07
    9
    -0.07
    1
    -0.07
     quot
    -0.07
    POSITIVE LOGITS
    åĪĽå»º
    0.15
    _CREATE
    0.14
     create
    0.14
    建ç«ĭ
    0.14
    .create
    0.13
    åĪ¶ä½ľ
    0.13
    åĪĽéĢłåĩº
    0.13
     creating
    0.13
     Ñģозд
    0.13
     ÑģозданиÑı
    0.13
    Activations Density 0.456%

    No Known Activations