© 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. 34200
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or digits

    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
    åĭĩæ°Ķ
    -0.09
    çĦ¦
    -0.08
    ful
    -0.08
    sti
    -0.08
    ÙĴ
    -0.08
    è¿Ļä¸ĢåĪĩ
    -0.08
    ;amp
    -0.08
    imits
    -0.08
    ä¹ĭæĺŁ
    -0.08
    çī¹æľĹ
    -0.08
    POSITIVE LOGITS
    wards
    0.10
    âĤ¬âĦ¢
    0.09
    çļĦä¸ĢäºĽ
    0.09
    FTER
    0.09
    å®īåħ¨æĢ§
    0.08
    extView
    0.08
     à¹Ĩ
    0.08
    çļĦä¸Ģåijĺ
    0.08
    orners
    0.08
    个å¤ļ
    0.08
    Activations Density 0.520%

    No Known Activations