© 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. 10227
    Prev
    Next
    INDEX
    Explanations

    Durham

    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
    ìļĶ
    -0.10
    ../../../
    -0.09
    ¶
    -0.09
    arily
    -0.09
    èĢħçļĦ
    -0.09
    ots
    -0.09
    verted
    -0.09
    Ùħا
    -0.08
    eral
    -0.08
    dent
    -0.08
    POSITIVE LOGITS
    é»İæĺİ
    0.10
    TreeWidgetItem
    0.10
    ingly
    0.10
    nable
    0.09
    vie
    0.09
     footing
    0.09
    Ãłng
    0.09
    vant
    0.09
    .chunk
    0.09
    meld
    0.09
    Activations Density 0.193%

    No Known Activations