© 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. 28069
    Prev
    Next
    INDEX
    Explanations

    more likely

    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
    asan
    -0.09
     BIT
    -0.09
    åı«å£°
    -0.08
     ÑģпеÑĨиалÑĮно
    -0.08
    åĴĮå°ļ
    -0.08
    (||
    -0.08
    èĬ±å¼Ģ
    -0.08
     غÙĬر
    -0.08
     ÑĢа
    -0.08
     вÑĭб
    -0.08
    POSITIVE LOGITS
    èĩ³äºİ
    0.10
    çı¾å¯¦
    0.10
    欢è¿İæĤ¨
    0.10
    è¿ħ
    0.09
    çİ°å®ŀ
    0.09
    çİ°åĩº
    0.09
    .Types
    0.09
    ãĥ¼ãĥĹ
    0.09
    颦
    0.09
    ä¸Ģä¸ĸ
    0.09
    Activations Density 0.090%

    No Known Activations