© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19358
    Prev
    Next
    INDEX
    Explanations

    early or late time periods

    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
    åѤ
    -0.10
    èįŀ
    -0.10
    çĤ¹åĩ»æŁ¥çľĭ
    -0.09
     Saud
    -0.09
    door
    -0.09
    Whole
    -0.08
    å¢ŀè¿Ľ
    -0.08
    imed
    -0.08
    íĴĢ
    -0.08
    ional
    -0.08
    POSITIVE LOGITS
     stages
    0.09
    èĩªæŁ¥
    0.08
     Kết
    0.08
    odcast
    0.08
    对çĿĢ
    0.08
    èĪŀè¹Ī
    0.08
    èĩªçĦ¶èĢĮ
    0.08
    .Completed
    0.08
    ç»ĵ
    0.08
    atform
    0.08
    Activations Density 0.039%

    No Known Activations