© 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. 22652
    Prev
    Next
    INDEX
    Explanations

    a + role or descriptor

    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
    åİĦ
    -0.09
    该æĢİä¹Ī
    -0.09
    æĺ¯ä¸Ģä½į
    -0.09
    Ñıд
    -0.09
    æĸ¹å¼ı
    -0.08
    被èªī为
    -0.08
    enk
    -0.08
    éĤ£ä½į
    -0.08
    hog
    -0.08
    oop
    -0.08
    POSITIVE LOGITS
     окÑĢÑĥ
    0.09
    -END
    0.09
    å¤§åĽ½
    0.08
     недо
    0.08
    æıIJ款
    0.08
    çľĭçĤ¹
    0.08
    atham
    0.08
    åģļçļĦäºĭ
    0.08
    éĶ¦
    0.08
    就没æľī
    0.08
    Activations Density 0.032%

    No Known Activations