© 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. 22552
    Prev
    Next
    INDEX
    Explanations

    connect with databases or services

    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
    éĺ¶æ®µæĢ§
    -0.09
    å½»åºķ
    -0.09
    Chron
    -0.09
    Invoker
    -0.08
    èģĮä¸ļæĬĢèĥ½
    -0.08
    overe
    -0.08
    æ¼Ķä¹ł
    -0.08
    ä¸įæĩĤ
    -0.08
    ayscale
    -0.08
    iture
    -0.08
    POSITIVE LOGITS
    纽带
    0.13
    éĥ½è§īå¾Ĺ
    0.10
    icut
    0.10
    .Conn
    0.10
    lest
    0.10
    /connect
    0.10
    inch
    0.10
    (connect
    0.10
    един
    0.10
    è¿ŀæİ¥
    0.09
    Activations Density 0.325%

    No Known Activations