© 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. 9736
    Prev
    Next
    INDEX
    Explanations

    black sabbath, zephyr, gap year

    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
    essage
    -0.11
    adora
    -0.10
    site
    -0.10
    Ñĩа
    -0.09
     Futures
    -0.09
    çł¥
    -0.09
    驺
    -0.09
    اش
    -0.09
    ç«
    -0.09
    andin
    -0.09
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.10
     Chambers
    0.09
     ep
    0.08
    ä¸Ģç«Ļ
    0.08
     pri
    0.08
    åĨ¥
    0.07
    毡
    0.07
    gue
    0.07
    wright
    0.07
    Facade
    0.07
    Activations Density 0.006%

    No Known Activations