© 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. 27823
    Prev
    Next
    INDEX
    Explanations

    time duration measurement

    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
    主æĦı
    -0.10
    åĿŁ
    -0.09
    çĸ®
    -0.09
    èѦ
    -0.09
    apas
    -0.09
    alach
    -0.09
    cente
    -0.08
    屦
    -0.08
    çĬ¯è§Ħ
    -0.08
    avar
    -0.08
    POSITIVE LOGITS
    iko
    0.09
    omi
    0.09
    æĢĴ
    0.08
    .Abs
    0.08
    çĶŁæ¶¯
    0.08
    odes
    0.08
    åĪĿ次
    0.08
    "And
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    çĴĢçĴ¨
    0.08
    Activations Density 0.066%

    No Known Activations