© 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. 61711
    Prev
    Next
    INDEX
    Explanations

    air drop, forward, deployment, operations

    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
    æİĴæ°Ķ
    -0.09
    èĽĭ
    -0.09
    .mas
    -0.09
    åĤ¨èĵĦ
    -0.09
    æĢ»ç®Ĺ
    -0.08
    èŁ¹
    -0.08
    åĵį
    -0.08
    åŀĨ
    -0.08
    京津
    -0.08
    èѦæĥķ
    -0.08
    POSITIVE LOGITS
    erb
    0.12
    å±ķå¼Ģ
    0.10
    à¹Ĥà¸Ķ
    0.10
     parach
    0.10
    空
    0.09
    Ñİ
    0.09
    Deployment
    0.09
    Declared
    0.09
    éĻįèIJ½
    0.09
    deployment
    0.08
    Activations Density 0.101%

    No Known Activations