© 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. 34914
    Prev
    Next
    INDEX
    Explanations

    hope

    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
    åĬ¬
    -0.10
    ern
    -0.09
    lets
    -0.09
    æīĵéĢļ
    -0.09
    4
    -0.08
    igi
    -0.08
    ä»Ģä¹Īæł·çļĦ
    -0.08
    0
    -0.08
     erst
    -0.08
    6
    -0.08
    POSITIVE LOGITS
     hope
    0.28
    å¸ĮæľĽ
    0.28
    hope
    0.22
    Hope
    0.22
     Hope
    0.20
    æľŁæľĽ
    0.19
    çĽ¼æľĽ
    0.19
    ä¿¡å¿ĥ
    0.19
     hopes
    0.18
    å¸ĮæľĽéĢļè¿ĩ
    0.18
    Activations Density 0.082%

    No Known Activations