© 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. 10875
    Prev
    Next
    INDEX
    Explanations

    structural or structure properties

    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
    OrCreate
    -0.09
    ä¸Ģ个éĩįè¦ģ
    -0.09
    .Reader
    -0.09
    mie
    -0.09
    çĭIJ
    -0.09
    iable
    -0.09
    quam
    -0.09
    é¦ĸ饰
    -0.08
     structural
    -0.08
    çĶ¨åĬĽ
    -0.08
    POSITIVE LOGITS
    ively
    0.15
     timeval
    0.13
    ally
    0.12
     ContentView
    0.12
    ured
    0.11
    urally
    0.10
    URED
    0.10
    ivism
    0.10
    ives
    0.10
    ural
    0.10
    Activations Density 0.071%

    No Known Activations