© 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. 33034
    Prev
    Next
    INDEX
    Explanations

    causation and effects

    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
    инÑĦ
    -0.09
    éħĴ
    -0.08
    ÑģÑĤÑĢел
    -0.08
    夫å¦ĩ
    -0.08
    æĥ«
    -0.08
    è£ģ
    -0.08
    .step
    -0.08
    å¯ĵ
    -0.08
    泡
    -0.08
    )'),
    -0.08
    POSITIVE LOGITS
    èĤłèĥĥ
    0.12
    第äºĮ天
    0.12
    ÑĢÑĥ
    0.10
    ä¸Ńæ¯Ĵ
    0.10
     ru
    0.10
    èĦ¾èĥĥ
    0.09
    ä¸Ģåij¨
    0.09
    èĪĮ头
    0.09
    ä¸Ģ楼
    0.09
    å½ĵ天
    0.09
    Activations Density 0.100%

    No Known Activations