© 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. 20147
    Prev
    Next
    INDEX
    Explanations

    desperate or threatened state

    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
    å½¹
    -0.10
    æŀķ
    -0.09
     weg
    -0.09
    è¨Ģè¡Į
    -0.09
    侵害
    -0.09
    éĹ»åIJį
    -0.09
    éĽªèĬ±
    -0.08
    é¼¾
    -0.08
    èĢķ
    -0.08
    åĮ»æĬ¤
    -0.08
    POSITIVE LOGITS
     desperation
    0.18
     desperate
    0.18
    çĿĢæĢ¥
    0.13
    åİĭåĬĽ
    0.12
    ç»ĿæľĽ
    0.12
    å®īåħ¨æĦŁ
    0.12
    æĢ¥äºİ
    0.11
    æĮ«
    0.11
    å¯Ĥå¯ŀ
    0.11
     compens
    0.10
    Activations Density 0.112%

    No Known Activations