© 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. 55005
    Prev
    Next
    INDEX
    Explanations

    control flow of energy or substances

    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
    aida
    -0.10
    åĪ»
    -0.10
    笼
    -0.09
    é¾Ļæ¹ĸ
    -0.08
    å»ĵ
    -0.08
    zon
    -0.08
    zza
    -0.08
    çĤĴ
    -0.08
    踢
    -0.08
    (sk
    -0.08
    POSITIVE LOGITS
    æµģåĬ¨
    0.17
    æµģåIJij
    0.16
     flow
    0.14
    Flow
    0.14
    è¿Ľåĩº
    0.13
     flowed
    0.13
    æµģ
    0.13
     flows
    0.13
     Flow
    0.12
    æµģãĤĮ
    0.12
    Activations Density 0.122%

    No Known Activations