© 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. 63043
    Prev
    Next
    INDEX
    Explanations

    Wen Zhang, Marijn, ologic studies

    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
    ettes
    -0.10
    oco
    -0.10
    ä¸įçĦ¶
    -0.09
    arium
    -0.09
    eds
    -0.09
    ëģĶ
    -0.09
    igator
    -0.09
    ä¸Ģç³»åĪĹ
    -0.09
    inke
    -0.09
    ħ
    -0.09
    POSITIVE LOGITS
    -minded
    0.14
    ³
    0.11
    est
    0.11
    ãģ¾ãģ¾
    0.10
    èĩ¾
    0.10
    ãģĹãģı
    0.10
    ities
    0.10
    entes
    0.10
     minded
    0.10
    aires
    0.09
    Activations Density 0.277%

    No Known Activations