© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35716
    Prev
    Next
    INDEX
    Explanations

    negative sentiment adjectives

    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
    飵
    -0.10
    éĩįå¿ĥ
    -0.09
    éŁ
    -0.09
    ãĥĻãĤ¹ãĥĪ
    -0.09
    æĺķ
    -0.09
    ected
    -0.09
    é»ij马
    -0.09
    æŀķ
    -0.09
    屿
    -0.09
    à¸Ľà¸£à¸°
    -0.09
    POSITIVE LOGITS
    å¼±
    0.16
    åı¯æĢľ
    0.16
     weak
    0.12
     Weak
    0.12
    Weak
    0.12
    weak
    0.12
     pathetic
    0.12
    羸
    0.12
     weakest
    0.11
    _weak
    0.10
    Activations Density 0.088%

    No Known Activations