© 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. 35052
    Prev
    Next
    INDEX
    Explanations

    converting to a different format

    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
    ths
    -0.09
    0
    -0.09
    lew
    -0.08
    5
    -0.08
    6
    -0.08
    æĿŀ
    -0.08
     Reserve
    -0.08
     веÑī
    -0.08
    thal
    -0.08
     same
    -0.08
    POSITIVE LOGITS
    缸åºĶçļĦ
    0.11
    éºŁ
    0.10
    åı¦ä¸Ģç§į
    0.10
     khoá
    0.10
    稽
    0.10
    æĻ°
    0.10
    æĶ¾åĪ°
    0.10
    åħķ
    0.10
    å¤ļç§įå½¢å¼ı
    0.10
    éĺı
    0.10
    Activations Density 0.143%

    No Known Activations