© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20796
    Prev
    Next
    INDEX
    Explanations

    rights and freedoms

    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
    åĽ½å®¶éĩįçĤ¹
    -0.11
    æĢ»å±Ģ
    -0.10
    æĶĢ
    -0.09
    Echo
    -0.09
    èĽĩ
    -0.09
    åĬłéĩį
    -0.09
    agger
    -0.09
    ÑĦон
    -0.09
    å¡«è¡¥
    -0.08
    _SCR
    -0.08
    POSITIVE LOGITS
    人æĿĥ
    0.18
    èĩªçĶ±
    0.17
     freedoms
    0.17
     freedom
    0.16
     liberty
    0.16
     Freedom
    0.15
    Freedom
    0.15
     liberties
    0.14
     Ñģвоб
    0.14
     liberté
    0.13
    Activations Density 0.101%

    No Known Activations