© 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. 8587
    Prev
    Next
    INDEX
    Explanations

    financial sentiment

    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
    å½ĵå±Ģ
    -0.11
    å½ĵä¹ĭ
    -0.11
    å½ĵéĢī
    -0.10
    æľªç»ı
    -0.09
    èģĺ
    -0.09
    å¾ģæ±Ĥ
    -0.09
    etros
    -0.09
    åijĪçİ°
    -0.09
    注å®ļ
    -0.09
    çIJ´
    -0.08
    POSITIVE LOGITS
    æĬ¢
    0.11
    ä¸įç¡®å®ļæĢ§
    0.10
    ÑģÑĤеÑĢ
    0.10
    eward
    0.09
    æħij
    0.09
    æĺİçĻ½äºĨ
    0.09
    ä¸įæĦ¿æĦı
    0.09
     âķ
    0.09
    å¿ĥ缮ä¸Ń
    0.09
    çIJĨæĢ§
    0.09
    Activations Density 0.043%

    No Known Activations