© 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. 35481
    Prev
    Next
    INDEX
    Explanations

    contents of or statements in

    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
    èĬ½
    -0.09
    åĹľ
    -0.09
    íĮIJ
    -0.09
    ä½Ĩä»į
    -0.08
    åī¯
    -0.08
     пÑĢавилÑĮно
    -0.08
    iciente
    -0.08
    æľĽ
    -0.08
    夸
    -0.08
    ÑģÑĤва
    -0.08
    POSITIVE LOGITS
    æīĭç»Ń
    0.10
    ç»Ĩå¾®
    0.10
    .Toolkit
    0.09
    轻微
    0.08
    eor
    0.08
    .src
    0.08
    yor
    0.08
    ä½ľåĵģåĨħ容
    0.08
    å©´å¹¼åĦ¿
    0.08
    äºĽ
    0.08
    Activations Density 0.161%

    No Known Activations