© 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. 62462
    Prev
    Next
    INDEX
    Explanations

    well used

    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
    ees
    -0.11
    лаг
    -0.10
    eer
    -0.09
    ette
    -0.09
    åįİ缼
    -0.09
    ť
    -0.09
    们
    -0.09
    ité
    -0.09
    ÑĪка
    -0.09
    ReadStream
    -0.08
    POSITIVE LOGITS
    -known
    0.13
    ness
    0.13
     جدا
    0.12
     enough
    0.12
     sûr
    0.12
    INGTON
    0.12
    come
    0.11
    ington
    0.11
    comed
    0.11
    -being
    0.11
    Activations Density 0.060%

    No Known Activations