© 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. 37157
    Prev
    Next
    INDEX
    Explanations

    freedom and liberal policies

    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
    çĭŃ
    -0.11
    ityEngine
    -0.10
    _OCC
    -0.10
     MSNBC
    -0.09
    robat
    -0.09
    /rss
    -0.09
    峡
    -0.09
    çİij
    -0.09
    ç»ĨèĬĤ
    -0.09
    _CRITICAL
    -0.09
    POSITIVE LOGITS
    èĩªçĶ±
    0.18
     freedom
    0.15
    宽æĿ¾
    0.14
    å¼ĢæĶ¾
    0.14
     free
    0.13
    宽容
    0.13
     freely
    0.13
     open
    0.13
     Ñģвобод
    0.13
    对å¤ĸå¼ĢæĶ¾
    0.12
    Activations Density 0.139%

    No Known Activations