© 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. 36368
    Prev
    Next
    INDEX
    Explanations

    participating in research 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
    ([]*
    -0.10
     Mand
    -0.09
     اÙĦصØŃ
    -0.09
    igit
    -0.09
    秽
    -0.09
     thẩm
    -0.09
    à¸ģระ
    -0.09
     indirect
    -0.08
    ureau
    -0.08
    ooth
    -0.08
    POSITIVE LOGITS
    åħ¥éĢī
    0.13
    åıĤä¸İèĢħ
    0.12
    çłĶ究人åijĺ
    0.12
    çļĦçłĶ究
    0.11
     participant
    0.11
    积æŀģåıĤä¸İ
    0.11
    æĭĽåĭŁ
    0.10
    è¯ķéªĮ
    0.10
     Participant
    0.10
    Participant
    0.10
    Activations Density 0.108%

    No Known Activations