© 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. 57012
    Prev
    Next
    INDEX
    Explanations

    court or government jurisdiction

    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
    oji
    -0.11
    º
    -0.10
    æľĪä¸ĭ
    -0.10
    ä¸ŃåĽ½æ¢¦
    -0.09
    å¢ĥçķĮ
    -0.09
    tered
    -0.09
    ëģĶ
    -0.09
    ãģĬãģĭ
    -0.09
    tering
    -0.09
    onet
    -0.09
    POSITIVE LOGITS
    ally
    0.15
    ä¸įæ¸ħ
    0.10
    ä¸įæĺİ
    0.10
    åĨħçļĦ
    0.10
    ALLY
    0.09
    没æĶ¶
    0.09
    nement
    0.09
    eer
    0.09
    _POINTER
    0.08
    naire
    0.08
    Activations Density 0.013%

    No Known Activations