© 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. 34637
    Prev
    Next
    INDEX
    Explanations

    siblings

    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
    umble
    -0.10
    .UserInfo
    -0.09
    åĮħ容
    -0.09
    illon
    -0.09
    fully
    -0.09
    äºĽ
    -0.09
    å°ıä¼Ļ
    -0.09
    mond
    -0.09
    iable
    -0.09
    down
    -0.09
    POSITIVE LOGITS
    sWith
    0.12
    ãģĦãģŁãĤī
    0.09
    yan
    0.09
    yo
    0.09
    ya
    0.09
    DNA
    0.09
    ij
    0.09
    ÑĢог
    0.09
    åīįèĢħ
    0.08
    èle
    0.08
    Activations Density 0.008%

    No Known Activations