© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47717
    Prev
    Next
    INDEX
    Explanations

    controversy

    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
    itud
    -0.11
    ãģĭãĤĬ
    -0.10
    itude
    -0.10
    ÑĮÑı
    -0.10
    ruptcy
    -0.09
    studio
    -0.09
    cape
    -0.08
    rices
    -0.08
    startup
    -0.08
    çIJĨ论ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħ
    0.11
    ous
    0.11
    ç¬ijç¬ij
    0.10
    ously
    0.10
    jit
    0.10
    ä¹ĭ声
    0.10
    .Argument
    0.09
    ä¹İ
    0.09
    å·²ä¹ħçļĦ
    0.09
    æĢ§çļĦ
    0.09
    Activations Density 0.011%

    No Known Activations