© 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. 34002
    Prev
    Next
    INDEX
    Explanations

    training and job roles

    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
    çĩ§
    -0.11
    oted
    -0.09
    æī§
    -0.09
    AJOR
    -0.09
    æ£ī
    -0.09
     зай
    -0.09
    æµ·åĨħå¤ĸ
    -0.09
    éķ¿éķ¿
    -0.09
    éĻĨ
    -0.08
    åĨ¢
    -0.08
    POSITIVE LOGITS
    åŁ¹è®Ń
    0.12
    åijĺå·¥
    0.09
     train
    0.08
     training
    0.08
     Units
    0.08
     Ã¶ÄŁren
    0.08
    宵
    0.08
     employees
    0.08
    å»ĵ
    0.08
    Module
    0.08
    Activations Density 0.063%

    No Known Activations