© 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. 50074
    Prev
    Next
    INDEX
    Explanations

    architecture, design, and art fields

    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
    reck
    -0.10
    墨
    -0.09
    æįº
    -0.09
     SEAL
    -0.09
     Gä
    -0.09
    çĶ»çĶ»
    -0.08
    淹没
    -0.08
    åįĸåĩº
    -0.08
    /theme
    -0.08
    潤
    -0.08
    POSITIVE LOGITS
    æĶ¾åѦ
    0.09
     Spy
    0.09
     Alg
    0.09
    翻身
    0.08
    hp
    0.08
    æĸ¯çī¹
    0.08
    ä¸į失
    0.08
    ì¶ķ
    0.08
    çľŃ
    0.08
    éħįèµĦ
    0.08
    Activations Density 0.276%

    No Known Activations