© 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. 55323
    Prev
    Next
    INDEX
    Explanations

    run

    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
     Dexter
    -0.09
    尤为éĩįè¦ģ
    -0.08
    ãĥIJãĤ¹
    -0.08
    æīĵäºĨ
    -0.08
    姻
    -0.08
    empo
    -0.08
    à¹Ĥย
    -0.08
    ãĥijãĤ½
    -0.08
    @qq
    -0.08
    尤为
    -0.08
    POSITIVE LOGITS
    rides
    0.09
    æĤĸ
    0.09
    rum
    0.09
    visor
    0.09
    rick
    0.09
    é²ĩ
    0.08
    gra
    0.08
    æµ·åı£
    0.08
    rub
    0.08
    ä¸Ģåı°
    0.08
    Activations Density 0.031%

    No Known Activations