© 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. 20716
    Prev
    Next
    INDEX
    Explanations

    politics and news publications

    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
    otec
    -0.10
    轸
    -0.09
    çī¢åĽº
    -0.09
    noch
    -0.08
     Ing
    -0.08
    æľī幸
    -0.08
    more
    -0.08
    Ñĥма
    -0.07
    oka
    -0.07
    warts
    -0.07
    POSITIVE LOGITS
    ié
    0.10
    ÑĤал
    0.10
    çĿ¬
    0.10
    æĶ¾åĩº
    0.09
    èµij
    0.09
    ä¸Ģ头
    0.09
    بÙĬÙĨ
    0.09
    ä¸įæ¸ħ
    0.09
    Ø´Ùģ
    0.08
    iendo
    0.08
    Activations Density 0.004%

    No Known Activations