© 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. 48317
    Prev
    Next
    INDEX
    Explanations

    offshore industry

    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
    tone
    -0.10
    æªĶ
    -0.10
    ikk
    -0.10
    åħļåĴĮåĽ½å®¶
    -0.09
    èĪį
    -0.09
    ä¸Ńæŀ¢
    -0.09
    ual
    -0.09
    ê¼´
    -0.09
    usch
    -0.09
    å¹ħ
    -0.08
    POSITIVE LOGITS
    /off
    0.11
    erman
    0.10
    ered
    0.10
    æĺİçıł
    0.09
    SCO
    0.09
     него
    0.09
    ä»İæĿ¥
    0.09
    滩
    0.09
    -facing
    0.09
    дÑĥм
    0.08
    Activations Density 0.007%

    No Known Activations