© 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. 31398
    Prev
    Next
    INDEX
    Explanations

    epigenetics and gene regulation

    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
    æĭĽ
    -0.12
    bone
    -0.09
    çļĦæľ¬è´¨
    -0.09
    磼
    -0.08
    edImage
    -0.08
    æĶ¯
    -0.08
     Emanuel
    -0.08
    åıĹ害
    -0.08
     bone
    -0.08
    olut
    -0.08
    POSITIVE LOGITS
    缴æݥ影åĵį
    0.10
    æĺ¼å¤ľ
    0.10
    èĮĹ
    0.09
    è°ĥçIJĨ
    0.09
    åĴ¸
    0.09
    楼å¸Ĥ
    0.09
     toll
    0.09
    æ·±
    0.09
    è®°å¿Ĩ
    0.08
    亵
    0.08
    Activations Density 0.184%

    No Known Activations