© 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. 56262
    Prev
    Next
    INDEX
    Explanations

    ordeal suffering hardships experienced

    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
    è¸Ĭ
    -0.10
    èĽĽ
    -0.09
    åĢĴåľ¨
    -0.09
    æķ¬
    -0.08
    arus
    -0.08
    ç»ĨåĪĻ
    -0.08
    转åħ¥
    -0.08
    egt
    -0.08
    ake
    -0.08
    ä¸įä¸Ĭ
    -0.07
    POSITIVE LOGITS
    ç»ıåİĨ
    0.20
    ç¶ĵæŃ·
    0.18
    ç»ıåİĨäºĨ
    0.16
    ç»ıåİĨè¿ĩ
    0.15
    çļĦç»ıåİĨ
    0.14
    æī¿åıĹ
    0.14
    éĺħåİĨ
    0.14
    åİĨç»ı
    0.13
    沧æ¡ij
    0.12
     experiences
    0.12
    Activations Density 0.054%

    No Known Activations