© 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. 4479
    Prev
    Next
    INDEX
    Explanations

    as ... as

    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
    ä»Ķ
    -0.10
    eh
    -0.10
     Very
    -0.09
    篦
    -0.09
    ï¸ı
    -0.09
     VERY
    -0.09
    ä»Ģ
    -0.09
     very
    -0.08
    edral
    -0.08
     Apps
    -0.08
    POSITIVE LOGITS
    åħ³éĶ®
    0.09
    æĶ¾æīĭ
    0.09
    é«ĺçļĦ
    0.09
    çļĦåīįæıIJä¸ĭ
    0.09
    大çļĦ
    0.09
    æĸ°æĹ¶æľŁ
    0.09
    åĶ¤
    0.09
    ynchron
    0.09
    _EL
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.09
    Activations Density 0.012%

    No Known Activations