© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10333
    Prev
    Next
    INDEX
    Explanations

    words indicating selection or curation

    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
     ComVisible
    -0.10
    äºĪ
    -0.10
    çħ
    -0.09
    itics
    -0.09
     Injector
    -0.09
    æĹłçŁ¥
    -0.08
    è¹Ī
    -0.08
    æĶ¿åħļ
    -0.08
    arih
    -0.08
    è¾Ľåĭ¤
    -0.08
    POSITIVE LOGITS
    æĮijéĢī
    0.22
    ç²¾éĢī
    0.18
     selection
    0.18
    éģ´éĢī
    0.17
     selected
    0.17
    éĢīåĩº
    0.17
    éģ´
    0.17
    éĢīæĭ
    0.17
    çŃĽéĢī
    0.16
    éĢīæĭĶ
    0.16
    Activations Density 0.129%

    No Known Activations