© 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. 62378
    Prev
    Next
    INDEX
    Explanations

    optimism and positive 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
    eth
    -0.08
     ger
    -0.08
     Honor
    -0.08
    ä¸įéĢĤåIJĪ
    -0.08
    çºł
    -0.08
     Ethics
    -0.08
    çĹĴ
    -0.08
    馥
    -0.07
    æĿ¾
    -0.07
    å´Ń
    -0.07
    POSITIVE LOGITS
    ä¹IJè§Ĥ
    0.33
     optimistic
    0.23
     optimism
    0.22
    å¼ĢæľĹ
    0.19
    æĤ²è§Ĥ
    0.15
     upbeat
    0.14
    å±ķæľĽ
    0.14
    èĩªä¿¡
    0.14
    å¯¹æľªæĿ¥
    0.14
    çļĦä¿¡å¿ĥ
    0.14
    Activations Density 0.066%

    No Known Activations