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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11172
    Prev
    Next
    INDEX
    Explanations

    negative sentiment, emotion words

    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
    åłª
    -0.11
    æĭ³
    -0.09
    idan
    -0.09
    大å®Ĺ
    -0.09
    æĬ½
    -0.09
    大åĶIJ
    -0.08
    gers
    -0.08
    prox
    -0.08
    å¸Ĥå§Ķ
    -0.08
    æij¸ç´¢
    -0.08
    POSITIVE LOGITS
    ä¸Ĭä¸ĭ
    0.11
    缸è§ģ
    0.10
    为ä¹ĭ
    0.10
    æĹłæķ°
    0.09
    没å¿ħè¦ģ
    0.09
    ç³Ĭæ¶Ĥ
    0.09
    rovers
    0.09
    å«Įçĸij
    0.09
    失åİ»
    0.09
    å¹²äºĭ
    0.08
    Activations Density 0.035%

    No Known Activations