© 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. 36815
    Prev
    Next
    INDEX
    Explanations

    guilty parties and responsibility

    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
    éľ²
    -0.10
    .esp
    -0.10
    Ùħد
    -0.10
    éļ°
    -0.10
    å¬
    -0.09
    acular
    -0.09
    ãĤ¹ãĥĿ
    -0.09
     espionage
    -0.09
    ophilia
    -0.09
    Å¡t
    -0.09
    POSITIVE LOGITS
    èĤĩäºĭ
    0.13
     culp
    0.11
     responsible
    0.10
    ä½ľæ¡Ī
    0.09
    å¿ı
    0.09
    被认为æĺ¯
    0.09
    ä¹Łè¢«
    0.09
    责任
    0.09
    æī¿æĭħ责任
    0.09
     Orch
    0.08
    Activations Density 0.061%

    No Known Activations