© 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. 58408
    Prev
    Next
    INDEX
    Explanations

    arrangements, proposal, Copyright, Amazon Listing

    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
    éĴĿ
    -0.10
    驾
    -0.09
     Cly
    -0.09
    emin
    -0.08
    é»Ħæĺı
    -0.08
    丧
    -0.08
    åħĭèݱ
    -0.08
    owie
    -0.08
    ä¸Ī夫
    -0.08
    klä
    -0.08
    POSITIVE LOGITS
    ç»ıèIJ¥çIJĨ念
    0.09
    essa
    0.09
     xlink
    0.08
     Cron
    0.08
    fol
    0.08
    æĢ»è®¡
    0.08
     frosting
    0.08
    横
    0.08
    iz
    0.08
    олод
    0.08
    Activations Density 0.068%

    No Known Activations