© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37214
    Prev
    Next
    INDEX
    Explanations

    image size and dimensions

    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
    éĥ¨åĪĨåĨħ容
    -0.10
    ä½ĵ温
    -0.10
    åīįä¸ī
    -0.09
    åŦ
    -0.09
    CppClass
    -0.09
    .Operator
    -0.09
    неж
    -0.09
    /ge
    -0.09
    adders
    -0.09
    esen
    -0.09
    POSITIVE LOGITS
    尺寸
    0.11
    6
    0.09
    9
    0.09
    7
    0.09
    4
    0.09
    ç¥Ń
    0.09
    è£ģ
    0.09
     Nim
    0.09
     dimensions
    0.09
     size
    0.09
    Activations Density 0.087%

    No Known Activations