© 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. 4711
    Prev
    Next
    INDEX
    Explanations

    activation of biological pathways

    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
    cape
    -0.09
    ens
    -0.09
    esh
    -0.09
    alytics
    -0.09
    PILE
    -0.09
    .tie
    -0.09
    duc
    -0.09
    ãģ¤ãģĭ
    -0.09
    媳
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    POSITIVE LOGITS
    çİĩè¾¾
    0.10
    /pass
    0.10
    碼
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    åĴĴ
    0.10
    çİĩè¾¾åĪ°
    0.09
    ä¸įäºĨ
    0.09
    ned
    0.09
    ally
    0.09
    /de
    0.09
    Activations Density 0.091%

    No Known Activations