© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21494
    Prev
    Next
    INDEX
    Explanations

    Join, Sign, By, Overview

    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
    Lorem
    -0.09
    1
    -0.09
    2
    -0.08
    4
    -0.08
    es
    -0.07
    6
    -0.07
    3
    -0.07
    8
    -0.07
    ,
    -0.07
    éĹ´
    -0.07
    POSITIVE LOGITS
    åħ¶å®ĥ
    0.10
    duk
    0.10
    à¸Ńำà¸Ļวยà¸Ħวาม
    0.10
    èĢĮåĩº
    0.10
    èµĦæºIJæķ´åIJĪ
    0.09
    ãģ©ãĤĵãģ©
    0.09
    à¸Ĥà¸Ļา
    0.09
    èľĥ
    0.09
    ãģķãĤī
    0.09
    没æ³ķ
    0.09
    Activations Density 0.821%

    No Known Activations