© 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. 52791
    Prev
    Next
    INDEX
    Explanations

    disappointment and its variants

    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
    -0.13
    à¹Į
    -0.09
    æĶ¯éħį
    -0.09
    instein
    -0.09
    åħ³éĶ®æŶåĪ»
    -0.09
    itarian
    -0.09
    ç´§å¼ł
    -0.09
    åı¨
    -0.09
    è¾ĺ
    -0.08
    æķijåĬ©
    -0.08
    POSITIVE LOGITS
    iable
    0.11
    ingly
    0.10
    /errors
    0.09
    ably
    0.09
    agrams
    0.09
    ype
    0.09
    odor
    0.09
    ment
    0.09
    ening
    0.09
    æīĢåľ¨
    0.09
    Activations Density 0.003%

    No Known Activations