© 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. 30395
    Prev
    Next
    INDEX
    Explanations

    feeling alone or isolated

    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
    ä¸įèµ·
    -0.09
    mani
    -0.09
    alem
    -0.09
    çĶ«
    -0.08
    ç½¢
    -0.08
    åĿĩåĮĢ
    -0.08
    åį·
    -0.08
    æ¶Īè´¹èĢħçļĦ
    -0.08
    åºļ
    -0.08
    夺
    -0.08
    POSITIVE LOGITS
    åѤçĭ¬
    0.31
    å¯Ĥå¯ŀ
    0.29
    åѤåįķ
    0.28
    åѤ
    0.23
    åѤç«ĭ
    0.22
     loneliness
    0.22
     lonely
    0.22
    å¯Ĥ
    0.20
     isolation
    0.20
    Lon
    0.20
    Activations Density 0.074%

    No Known Activations