© 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. 33055
    Prev
    Next
    INDEX
    Explanations

    offline use or functionality

    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
     Noon
    -0.10
    é²ľèī³
    -0.10
    èľĥ
    -0.09
    çĺ´
    -0.09
    veillance
    -0.09
    å¸ĪåĤħ
    -0.09
    骤
    -0.09
    inally
    -0.09
    åĮºåĪĨ
    -0.08
    inals
    -0.08
    POSITIVE LOGITS
     readonly
    0.09
    imap
    0.09
     pursuits
    0.09
    åģļ强
    0.09
    ASON
    0.09
    agens
    0.09
    perse
    0.08
     offline
    0.08
     Offline
    0.08
    лекÑģ
    0.08
    Activations Density 0.010%

    No Known Activations